First pyramid push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140d16ffaad54383d2f6b763cd1a3136c5332dbe974cd4ad746e0404540f26f5
-size 67272
+oid sha256:315681cb77c9aedb87c0d939338a26d23ab00e864f4868b5bb4dc850e582e221
+size 450510

Pyramids/Pyramids-1200012.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b41ef3209c824b587403e01a87d0604aafe68c8bdbb8d3814da9c9898863cbb
+size 450510

Pyramids/Pyramids-1200012.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a534a5733102e4e0c74abbcec52b497bfe916a04285896f61b232d36b475a108
+size 2999652

Pyramids/Pyramids-1400079.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2caec6ccdfef3c54537ed3b063ccac6b3c35ee50925ca287698fd9a875d00110
+size 450510

Pyramids/Pyramids-1400079.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4beef6e87dd07e5ac16768431546a889cb5dd9c14b11342e728b532809d95c08
+size 2999652

Pyramids/Pyramids-1499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b97950e7d20187778f53ef38e4ecad0b3fd7457d34481bfe0d5f4a5e1f23ad
+size 450510

Pyramids/Pyramids-1499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151447f4f9092e2cded7624f480b76ec8a15f77c6ffdfb26ba337616a91a9bfb
+size 2999652

Pyramids/Pyramids-1800095.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:315681cb77c9aedb87c0d939338a26d23ab00e864f4868b5bb4dc850e582e221
+size 450510

Pyramids/Pyramids-1800095.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56dfdb5ffa847da875fe798aebb8ca7518239f506620d1285b1f8743e0069920
+size 2999652

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:425a230063b8f25ebef89628478b0fb8740d410ceba4143c86b3242eea13ce8f
-size 518242
+oid sha256:7627d8bfeb957f44e6aaf788d9249cdecfdc8f2f9ae576821c6264db10a0e042
+size 2999202

Pyramids/events.out.tfevents.1728315135.5f52071ec81e.2454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7489e5bf708a1135b2b218437ac94fefee356a0172623f42d8b388256338da0c
+size 333463

Pyramids/events.out.tfevents.1728317363.5f52071ec81e.11637.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b24244649f6f1b6752701e319c14b9fa38c00d05a25558f38bbb824dde4865
+size 1423

Pyramids/events.out.tfevents.1728317417.5f52071ec81e.11925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57d9a87ebfee2948533992fd2f9323bb1e3e24f847393e7f9515f26f557b4bd
+size 73871

Pyramids/events.out.tfevents.1728318820.5f52071ec81e.17843.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d469794c5db84ebe7dafacf2f89310b05911b03184539773e12e01c5a1d45490
+size 63558

Pyramids/events.out.tfevents.1728319280.5f52071ec81e.19820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e1415c1e3aec700bb26e1c5e2f2269cff457b2530fb0c161409c8afa924402
+size 99699

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0005, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 2, "vis_encode_type": "nature_cnn", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.05, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 300000, "time_horizon": 128, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 2, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "resnet", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.03, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1800000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,11 +5,11 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0005
+      learning_rate: 0.0003
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 3
+      num_epoch: 2
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
@@ -17,9 +17,9 @@ behaviors:
     checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 64
+      hidden_units: 256
       num_layers: 2
-      vis_encode_type: nature_cnn
+      vis_encode_type: resnet
       memory: null
       goal_conditioning_type: hyper
       deterministic: false
@@ -37,10 +37,10 @@ behaviors:
           deterministic: false
       rnd:
         gamma: 0.99
-        strength: 0.05
+        strength: 0.03
         network_settings:
           normalize: false
-          hidden_units: 64
+          hidden_units: 128
           num_layers: 2
           vis_encode_type: simple
           memory: null
@@ -51,9 +51,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 300000
+    max_steps: 1800000
     time_horizon: 128
-    summary_freq: 10000
+    summary_freq: 30000
     threaded: false
     self_play: null
     behavioral_cloning: null
@@ -82,8 +82,8 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55262 [Flags] 2 [Guid] 3903973358 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55053 [Flags] 2 [Guid] 2569294608 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.120 seconds
+- Completed reload, in  0.093 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.253280 ms
+UnloadTime: 0.803179 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2595 frames, [32.0 KB-64.0 KB]: 2615 frames, [64.0 KB-128.0 KB]: 430 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 473 frames, [32.0 KB-64.0 KB]: 4794 frames, [64.0 KB-128.0 KB]: 2254 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -123,17 +123,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -183,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -204,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 5342 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 49 frames, [1.0 MB-2.0 MB]: 7473 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11550
+  Peak main deferred allocation count 8886
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 5640 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 7521 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.7 MB
+      Peak Block count 2
+      Peak Allocated memory 25.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5641 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 7522 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.6 MB
+      Peak Allocated memory 21.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5640 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7521 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 5641 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 7522 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 5342 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 40 frames, [1.0 MB-2.0 MB]: 7482 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 5640 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 7521 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -288,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5641 frames
+      Peak usage frame count: [0-1.0 KB]: 7522 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 5641 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 7522 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [16.0 KB-32.0 KB]: 5641 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 7522 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1728314610570,"processId":11596,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1728320195958,"processId":19855,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5313839316368103,
-            "min": 0.5184337496757507,
-            "max": 1.59465754032135,
-            "count": 30
+            "value": 0.3509610891342163,
+            "min": 0.3087957203388214,
+            "max": 0.36777380108833313,
+            "count": 14
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5126.7919921875,
-            "min": 5093.09326171875,
-            "max": 16329.29296875,
-            "count": 30
+            "value": 10590.6015625,
+            "min": 3339.9345703125,
+            "max": 11009.6767578125,
+            "count": 14
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 261.5739130434783,
+            "min": 208.8709677419355,
+            "max": 333.15555555555557,
+            "count": 14
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30081.0,
+            "min": 6475.0,
+            "max": 30810.0,
+            "count": 14
         },
         "Pyramids.Step.mean": {
-            "value": 299885.0,
-            "min": 9984.0,
-            "max": 299885.0,
-            "count": 30
+            "value": 1799967.0,
+            "min": 1409913.0,
+            "max": 1799967.0,
+            "count": 14
         },
         "Pyramids.Step.sum": {
-            "value": 299885.0,
-            "min": 9984.0,
-            "max": 299885.0,
-            "count": 30
+            "value": 1799967.0,
+            "min": 1409913.0,
+            "max": 1799967.0,
+            "count": 14
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.039451178163290024,
-            "min": -0.09713312983512878,
-            "max": 0.005632735323160887,
-            "count": 30
+            "value": 0.6859020590782166,
+            "min": 0.578832745552063,
+            "max": 0.6859020590782166,
+            "count": 14
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -3.2349965572357178,
-            "min": -7.867783546447754,
-            "max": 0.46751704812049866,
-            "count": 30
+            "value": 200.2834014892578,
+            "min": 53.8724479675293,
+            "max": 200.2834014892578,
+            "count": 14
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.28675106167793274,
-            "min": 0.28675106167793274,
-            "max": 4.758534908294678,
-            "count": 30
+            "value": 21.957359313964844,
+            "min": 2.9718246459960938,
+            "max": 21.957359313964844,
+            "count": 14
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 23.513587951660156,
-            "min": 23.513587951660156,
-            "max": 385.44134521484375,
-            "count": 30
+            "value": 6411.548828125,
+            "min": 264.4924011230469,
+            "max": 6411.548828125,
+            "count": 14
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.720510334675682,
+            "min": 1.629107512453551,
+            "max": 1.7911290161071285,
+            "count": 14
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 199.5791988223791,
+            "min": 55.524999499320984,
+            "max": 199.5791988223791,
+            "count": 14
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.720510334675682,
+            "min": 1.629107512453551,
+            "max": 1.7911290161071285,
+            "count": 14
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 199.5791988223791,
+            "min": 55.524999499320984,
+            "max": 199.5791988223791,
+            "count": 14
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.22894134176172445,
+            "min": 0.22894134176172445,
+            "max": 0.3622605609319483,
+            "count": 14
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 26.557195644360036,
+            "min": 7.3203921407694,
+            "max": 32.60345048387535,
+            "count": 14
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06659919462981634,
-            "min": 0.06458665847948378,
-            "max": 0.07921396348625422,
-            "count": 30
+            "value": 0.07270944114134181,
+            "min": 0.06266858351548708,
+            "max": 0.07270944114134181,
+            "count": 14
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.3329959731490817,
-            "min": 0.14816739533067114,
-            "max": 0.39606981743127107,
-            "count": 30
+            "value": 1.0179321759787854,
+            "min": 0.27831401882576756,
+            "max": 1.0420461169269402,
+            "count": 14
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.005549917463455738,
-            "min": 0.0007214731828929779,
-            "max": 2.6744915254724524,
-            "count": 30
+            "value": 21.68147027705397,
+            "min": 0.471697402519307,
+            "max": 21.68147027705397,
+            "count": 14
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.02774958731727869,
-            "min": 0.0036073659144648896,
-            "max": 5.348983050944905,
-            "count": 30
+            "value": 303.54058387875557,
+            "min": 1.9932998442091048,
+            "max": 303.54058387875557,
+            "count": 14
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.829431767466678e-06,
-            "min": 7.829431767466678e-06,
-            "max": 0.0004897600020479999,
-            "count": 30
+            "value": 2.424611096591275e-06,
+            "min": 2.424611096591275e-06,
+            "max": 6.578182807274999e-05,
+            "count": 14
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 3.914715883733339e-05,
-            "min": 3.914715883733339e-05,
-            "max": 0.001877886791089333,
-            "count": 30
+            "value": 3.394455535227785e-05,
+            "min": 3.394455535227785e-05,
+            "max": 0.0008766917744364446,
+            "count": 14
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10156586666666667,
-            "min": 0.10156586666666667,
-            "max": 0.19795200000000002,
-            "count": 30
+            "value": 0.10080817063492063,
+            "min": 0.10080817063492063,
+            "max": 0.12192725000000001,
+            "count": 14
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.5078293333333334,
-            "min": 0.39057066666666673,
-            "max": 0.8755773333333334,
-            "count": 30
+            "value": 1.4113143888888888,
+            "min": 0.48770900000000006,
+            "max": 1.7875094444444446,
+            "count": 14
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0001664300800000002,
-            "min": 0.0001664300800000002,
-            "max": 0.009795404800000001,
-            "count": 30
+            "value": 9.073624642857163e-05,
+            "min": 9.073624642857163e-05,
+            "max": 0.002200532275,
+            "count": 14
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.000832150400000001,
-            "min": 0.000832150400000001,
-            "max": 0.037570175600000005,
-            "count": 30
+            "value": 0.0012703074500000028,
+            "min": 0.0012703074500000028,
+            "max": 0.0293337992,
+            "count": 14
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.04801112040877342,
-            "min": 0.04801112040877342,
-            "max": 1.7646175622940063,
-            "count": 30
+            "value": 0.027669908478856087,
+            "min": 0.027669908478856087,
+            "max": 0.03692689538002014,
+            "count": 14
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.2400556057691574,
-            "min": 0.2138153612613678,
-            "max": 3.5292351245880127,
-            "count": 30
+            "value": 0.3873787224292755,
+            "min": 0.14770758152008057,
+            "max": 0.49223601818084717,
+            "count": 14
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 30
+            "count": 14
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 30
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 902.6923076923077,
-            "min": 789.0,
-            "max": 999.0,
-            "count": 29
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 11735.0,
-            "min": 789.0,
-            "max": 15984.0,
-            "count": 29
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.2877538834626858,
-            "min": -1.0000000521540642,
-            "max": 1.2109999358654022,
-            "count": 29
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -3.7408004850149155,
-            "min": -16.000000834465027,
-            "max": 1.2109999358654022,
-            "count": 29
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.2877538834626858,
-            "min": -1.0000000521540642,
-            "max": 1.2109999358654022,
-            "count": 29
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -3.7408004850149155,
-            "min": -16.000000834465027,
-            "max": 1.2109999358654022,
-            "count": 29
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 2.248917204829363,
-            "min": 2.248917204829363,
-            "max": 113.37435679137707,
-            "count": 29
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 29.235923662781715,
-            "min": 17.16025671362877,
-            "max": 1813.989708662033,
-            "count": 29
+            "count": 14
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1728313768",
+        "start_time_seconds": "1728319279",
         "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1728314610"
+        "end_time_seconds": "1728320196"
     },
-    "total": 841.6716424780002,
+    "total": 916.5547743960005,
     "count": 1,
-    "self": 1.2226194330000908,
+    "self": 1.1799581080003918,
     "children": {
         "run_training.setup": {
-            "total": 0.07048000999975557,
+            "total": 0.06476543600001605,
             "count": 1,
-            "self": 0.07048000999975557
+            "self": 0.06476543600001605
         },
         "TrainerController.start_learning": {
-            "total": 840.3785430350003,
+            "total": 915.3100508520001,
             "count": 1,
-            "self": 0.7278264639689951,
+            "self": 0.5411470719573117,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.1418418749999546,
+                    "total": 2.24071387100048,
                     "count": 1,
-                    "self": 2.1418418749999546
+                    "self": 2.24071387100048
                 },
                 "TrainerController.advance": {
-                    "total": 837.4002390130313,
-                    "count": 18960,
-                    "self": 0.8135929070281236,
+                    "total": 912.4310510820433,
+                    "count": 26117,
+                    "self": 0.5757557350352727,
                     "children": {
                         "env_step": {
-                            "total": 614.3581447360061,
-                            "count": 18960,
-                            "self": 571.7373430280154,
+                            "total": 710.9093044849951,
+                            "count": 26117,
+                            "self": 649.9562996429831,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 42.185202114984804,
-                                    "count": 18960,
-                                    "self": 2.2292223449462654,
+                                    "total": 60.62759578393161,
+                                    "count": 26117,
+                                    "self": 1.8369352299632737,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 39.95597977003854,
-                                            "count": 18803,
-                                            "self": 39.95597977003854
+                                            "total": 58.79066055396834,
+                                            "count": 25071,
+                                            "self": 58.79066055396834
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.435599593005918,
-                                    "count": 18960,
+                                    "total": 0.3254090580803677,
+                                    "count": 26117,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 838.1444552279972,
-                                            "count": 18960,
+                                            "total": 913.3407672259527,
+                                            "count": 26117,
                                             "is_parallel": true,
-                                            "self": 324.62054183996815,
+                                            "self": 311.62826983305786,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0029286159997354844,
+                                                            "total": 0.0031315679998442647,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000948376999986067,
+                                                            "self": 0.0009635180003897403,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0019802389997494174,
+                                                                    "total": 0.0021680499994545244,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0019802389997494174
+                                                                    "self": 0.0021680499994545244
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06471674900012658,
+                                                            "total": 0.09401083200009452,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008223410000027798,
+                                                            "self": 0.0006287340002018027,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005496369999491435,
+                                                                    "total": 0.0005019809996156255,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005496369999491435
+                                                                    "self": 0.0005019809996156255
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0597803919999933,
+                                                                    "total": 0.09124633700048435,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0597803919999933
+                                                                    "self": 0.09124633700048435
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0035643790001813613,
+                                                                    "total": 0.0016337799997927505,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004760600008921756,
+                                                                    "self": 0.0003371640004843357,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0030883189992891857,
+                                                                            "total": 0.0012966159993084148,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0030883189992891857
+                                                                            "self": 0.0012966159993084148
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 513.5239133880291,
-                                                    "count": 18959,
+                                                    "total": 601.7124973928949,
+                                                    "count": 26116,
                                                     "is_parallel": true,
-                                                    "self": 15.362981307011978,
+                                                    "self": 13.173401732853563,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 9.676796632009882,
-                                                            "count": 18959,
+                                                            "total": 9.298754634973193,
+                                                            "count": 26116,
                                                             "is_parallel": true,
-                                                            "self": 9.676796632009882
+                                                            "self": 9.298754634973193
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 449.0799627340075,
-                                                            "count": 18959,
+                                                            "total": 539.8244959001067,
+                                                            "count": 26116,
                                                             "is_parallel": true,
-                                                            "self": 449.0799627340075
+                                                            "self": 539.8244959001067
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 39.40417271499973,
-                                                            "count": 18959,
+                                                            "total": 39.41584512496138,
+                                                            "count": 26116,
                                                             "is_parallel": true,
-                                                            "self": 8.550509574921307,
+                                                            "self": 8.129025020915833,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 30.853663140078424,
-                                                                    "count": 151672,
+                                                                    "total": 31.286820104045546,
+                                                                    "count": 208928,
                                                                     "is_parallel": true,
-                                                                    "self": 30.853663140078424
+                                                                    "self": 31.286820104045546
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 222.22850136999705,
-                            "count": 18960,
-                            "self": 1.2491594040452583,
+                            "total": 200.94599086201288,
+                            "count": 26117,
+                            "self": 1.07309663295473,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 45.57653859195307,
-                                    "count": 18960,
-                                    "self": 45.57653859195307
+                                    "total": 54.34334475605556,
+                                    "count": 26117,
+                                    "self": 54.253657134056084,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.08968762199947378,
+                                            "count": 1,
+                                            "self": 0.08968762199947378
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 175.40280337399872,
-                                    "count": 127,
-                                    "self": 108.74284132002003,
+                                    "total": 145.5295494730026,
+                                    "count": 189,
+                                    "self": 81.035269021967,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 66.65996205397869,
-                                            "count": 6864,
-                                            "self": 66.65996205397869
+                                            "total": 64.49428045103559,
+                                            "count": 6066,
+                                            "self": 64.49428045103559
                                         }
                                     }
                                 }
@@ -369,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.5430000530614052e-06,
+                    "total": 1.5699997675255872e-06,
                     "count": 1,
-                    "self": 1.5430000530614052e-06
+                    "self": 1.5699997675255872e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10863414000004923,
+                    "total": 0.09713725699930364,
                     "count": 1,
-                    "self": 0.0009575519998179516,
+                    "self": 0.0016087909989437321,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10767658800023128,
+                            "total": 0.09552846600035991,
                             "count": 1,
-                            "self": 0.10767658800023128
+                            "self": 0.09552846600035991
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 300013,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-300013.onnx",
+                "steps": 1000060,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000060.onnx",
                 "reward": null,
-                "creation_time": 1728314609.4122756,
+                "creation_time": 1728317365.6363008,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-300013.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000060.pt"
+                ]
+            },
+            {
+                "steps": 1200012,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200012.onnx",
+                "reward": 1.7082499526441097,
+                "creation_time": 1728317865.7540748,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1200012.pt"
+                ]
+            },
+            {
+                "steps": 1400079,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1400079.onnx",
+                "reward": 1.5549999922513962,
+                "creation_time": 1728319267.4209766,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1400079.pt"
+                ]
+            },
+            {
+                "steps": 1499966,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499966.onnx",
+                "reward": 1.814666638771693,
+                "creation_time": 1728319506.5698311,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499966.pt"
+                ]
+            },
+            {
+                "steps": 1800095,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1800095.onnx",
+                "reward": 1.7895000129938126,
+                "creation_time": 1728320194.8228204,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1800095.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 300013,
+            "steps": 1800095,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1728314609.4122756,
+            "reward": 1.7895000129938126,
+            "creation_time": 1728320194.8228204,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-300013.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1800095.pt"
             ]
         }
     },