Increase max_steps to 2e6

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2aaf4892107fa4ddcf44e9eaa1f01758c65b0d0bf9006213197d888a311102
+oid sha256:72a9917d285a4268590f37fe51ff328826f0da22edb36222480865bf48ff7378
 size 650646

SnowballTarget/SnowballTarget-1049976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c83b25f615f15bbe7a93f687a14432ce1ceb289dad6433da36814bf7d6e61ab
+size 650646

SnowballTarget/SnowballTarget-1049976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cde932b3c9125f70a3d9459a034aeb5688d9c254eb995a09ba923e6d725fd8
+size 3850214

SnowballTarget/SnowballTarget-1099992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c9f775d6471529fa2010ca08bfeeddb479a3c769d363aa42317077c07c075a
+size 650646

SnowballTarget/SnowballTarget-1099992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129fab420e420182d51fc76626db0a4b2a87edc9bc73985776c4111374c054c1
+size 3850214

SnowballTarget/SnowballTarget-1149936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a011ca73a0d08adb431a9106fb0a22c8f23d8568fe5640330d9862f1bd38c5
+size 650646

SnowballTarget/SnowballTarget-1149936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75e563a2ed36ee065b1c6771b86f1acc77406f3e1dfee67bc839b62c23958758
+size 3850214

SnowballTarget/SnowballTarget-1199960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e209447305cd6f40e859b70131ba7e6d4fa6d19ab47a4c70cff390bf40f53d2
+size 650646

SnowballTarget/SnowballTarget-1199960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d5dffd0621ae4992da5db3491a594480dd5dd66f95fb576ae84e2185fbd5b1
+size 3850214

SnowballTarget/SnowballTarget-1249984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2da7a00463e6a581d7df4b7510165d2544439aa6077f91f533b36147a691539
+size 650646

SnowballTarget/SnowballTarget-1249984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917438351d4450691184ad24f193cfe7eb78427f4ac4e56539872adf70ad60ac
+size 3850214

SnowballTarget/SnowballTarget-1299984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a35fd2f0b5017a7a185daffacb4f5e445086bdf043febd246e99d5883d4c3e2
+size 650646

SnowballTarget/SnowballTarget-1299984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217076a0572b63143218ba309578c0724d71ca4d482ed3d041e76d619caab5f2
+size 3850214

SnowballTarget/SnowballTarget-1349944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946603011e6630395bf862bb606143f1f88187fb5771c1fc69e927719da2d294
+size 650646

SnowballTarget/SnowballTarget-1349944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266351cabab3794d602fa5d9a62ff5784e8df9f7fdbb25dd75ea65d9b6e5b9a8
+size 3850214

SnowballTarget/SnowballTarget-1399968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9596631c4d72d6e2701a4bc91e3a2b48b087a260ece055a7b384487b94e8e48b
+size 650646

SnowballTarget/SnowballTarget-1399968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afd4dc5aaf782fe1848ad5c2863504f1f31ee6200535ce251c468faff34e1091
+size 3850214

SnowballTarget/SnowballTarget-1401400.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a9917d285a4268590f37fe51ff328826f0da22edb36222480865bf48ff7378
+size 650646

SnowballTarget/SnowballTarget-1401400.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36608b252a6ba422e16db3df0eb607c55baed7b48d80a7eb60eac53a46257d6b
+size 3850214

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8300b93fc65f78502f132a54b2a63617918f24d063f85e411d0cc478799dee95
+size 650646

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7230a9bc785e9eb0c79b4e7ef3ffd1ffa40196a7cea6dabf828613e96b4d628
+size 3850075

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37feea74f5e6d0b28937964d3b391dc56db774b00bfeffa8c6b2538ced8d3d47
+oid sha256:10fb77267989bdbbf6b0ee55545bf4bbfb747755468a382a9ef0cd02c1901840
 size 3849250

SnowballTarget/events.out.tfevents.1735828442.6ae3c6a60500.11819.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e8c1d329097f03d01c7e0615dcaff578ac6830f0f6cb90b708da3814a02572
+size 131757

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 512, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 2000000
     time_horizon: 64
     summary_freq: 10000
     threaded: false
@@ -66,10 +66,10 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ 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  0.079 seconds
+- Completed reload, in  0.083 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)
@@ -42,15 +42,16 @@ 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: 0.628396 ms
+UnloadTime: 0.639381 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 37585 frames, [16.0 KB-32.0 KB]: 637 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
@@ -78,7 +79,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -166,22 +167,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 12703 frames, [8.0 MB-16.0 MB]: 25520 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Block count 2
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 38223 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.7 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -195,7 +196,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +211,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 36785 frames, [64.0 KB-128.0 KB]: 1438 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 38223 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +229,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38223 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38222 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -246,13 +247,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 38223 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 38223 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,50 +1,358 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.7701504230499268,
+            "min": 0.7656258344650269,
+            "max": 2.890308141708374,
+            "count": 140
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7929.46875,
+            "min": 7396.3359375,
+            "max": 29528.98046875,
+            "count": 140
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 1399968.0,
+            "min": 9952.0,
+            "max": 1399968.0,
+            "count": 140
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 1399968.0,
+            "min": 9952.0,
+            "max": 1399968.0,
+            "count": 140
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 14.166781425476074,
+            "min": -0.12361296266317368,
+            "max": 14.166781425476074,
+            "count": 140
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2890.0234375,
+            "min": -23.980915069580078,
+            "max": 2890.0234375,
+            "count": 140
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 140
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 140
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 27.581818181818182,
+            "min": 2.7045454545454546,
+            "max": 28.4,
+            "count": 140
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1517.0,
+            "min": 119.0,
+            "max": 1562.0,
+            "count": 140
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 27.581818181818182,
+            "min": 2.7045454545454546,
+            "max": 28.4,
+            "count": 140
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1517.0,
+            "min": 119.0,
+            "max": 1562.0,
+            "count": 140
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 140
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 140
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.03238388441783923,
+            "min": 0.027749783229955936,
+            "max": 0.04213238783995621,
+            "count": 133
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.03238388441783923,
+            "min": 0.027749783229955936,
+            "max": 0.04213238783995621,
+            "count": 133
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.15203782301100474,
+            "min": 0.08559608033725194,
+            "max": 0.31449879159530003,
+            "count": 133
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.15203782301100474,
+            "min": 0.08559608033725194,
+            "max": 0.31449879159530003,
+            "count": 133
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 9.145326951559998e-05,
+            "min": 9.145326951559998e-05,
+            "max": 0.00029836320054560004,
+            "count": 133
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 9.145326951559998e-05,
+            "min": 9.145326951559998e-05,
+            "max": 0.00029836320054560004,
+            "count": 133
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.13048440000000006,
+            "min": 0.13048440000000006,
+            "max": 0.19945440000000006,
+            "count": 133
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.13048440000000006,
+            "min": 0.13048440000000006,
+            "max": 0.19945440000000006,
+            "count": 133
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0015311715600000006,
+            "min": 0.0015311715600000006,
+            "max": 0.0049727745600000005,
+            "count": 133
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0015311715600000006,
+            "min": 0.0015311715600000006,
+            "max": 0.0049727745600000005,
+            "count": 133
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1735827901",
+        "start_time_seconds": "1735828441",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1735827904"
+        "end_time_seconds": "1735831086"
     },
-    "total": 2.8816538609999043,
+    "total": 2645.0431771169997,
     "count": 1,
-    "self": 0.43308371500006615,
+    "self": 0.2702252909998606,
     "children": {
         "run_training.setup": {
-            "total": 0.05424889000005351,
+            "total": 0.056339447000027576,
             "count": 1,
-            "self": 0.05424889000005351
+            "self": 0.056339447000027576
         },
         "TrainerController.start_learning": {
-            "total": 2.3943212559997846,
+            "total": 2644.716612379,
             "count": 1,
-            "self": 0.00013261500043881824,
+            "self": 2.357972935955786,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.057805143999758,
+                    "total": 2.0717897399999856,
                     "count": 1,
-                    "self": 2.057805143999758
+                    "self": 2.0717897399999856
+                },
+                "TrainerController.advance": {
+                    "total": 2640.130034937044,
+                    "count": 127410,
+                    "self": 2.4775885128533446,
+                    "children": {
+                        "env_step": {
+                            "total": 2035.083508942159,
+                            "count": 127410,
+                            "self": 1551.4433312870374,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 482.1545468320578,
+                                    "count": 127410,
+                                    "self": 8.463040096167788,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 473.69150673589,
+                                            "count": 127410,
+                                            "self": 473.69150673589
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.4856308230637296,
+                                    "count": 127409,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2637.2616070511426,
+                                            "count": 127409,
+                                            "is_parallel": true,
+                                            "self": 1275.1481269522542,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0023126549999687995,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007755520000500837,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015371029999187158,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015371029999187158
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.048304481000286614,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006531300005008234,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003851729998132214,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003851729998132214
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.045396382000035373,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.045396382000035373
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001869795999937196,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00036458299928199267,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0015052130006552034,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0015052130006552034
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1362.1134800988884,
+                                                    "count": 127408,
+                                                    "is_parallel": true,
+                                                    "self": 69.0470171870029,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 38.201372316096695,
+                                                            "count": 127408,
+                                                            "is_parallel": true,
+                                                            "self": 38.201372316096695
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1036.73148657187,
+                                                            "count": 127408,
+                                                            "is_parallel": true,
+                                                            "self": 1036.73148657187
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 218.1336040239189,
+                                                            "count": 127408,
+                                                            "is_parallel": true,
+                                                            "self": 38.394573956658405,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 179.7390300672605,
+                                                                    "count": 1274080,
+                                                                    "is_parallel": true,
+                                                                    "self": 179.7390300672605
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 602.5689374820317,
+                            "count": 127409,
+                            "self": 2.6347049030027847,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 190.8393916780292,
+                                    "count": 127409,
+                                    "self": 188.12887053103032,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.7105211469988717,
+                                            "count": 28,
+                                            "self": 2.7105211469988717
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 409.09484090099977,
+                                    "count": 134,
+                                    "self": 285.5651750940451,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 123.52966580695465,
+                                            "count": 8142,
+                                            "self": 123.52966580695465
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.0229996405541897e-06,
+                    "total": 1.2780001270584762e-06,
                     "count": 1,
-                    "self": 1.0229996405541897e-06
+                    "self": 1.2780001270584762e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.33638247399994725,
+                    "total": 0.15681348799989792,
                     "count": 1,
-                    "self": 0.0011107169998467725,
+                    "self": 0.0012386159996822244,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3352717570001005,
+                            "total": 0.1555748720002157,
                             "count": 1,
-                            "self": 0.3352717570001005
+                            "self": 0.1555748720002157
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,76 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 7.636363636363637,
-                "creation_time": 1735826926.6402884,
+                "steps": 999952,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 26.87878787878788,
+                "creation_time": 1735830342.4347098,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-999952.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 11.06060606060606,
-                "creation_time": 1735827023.1901886,
+                "steps": 1049976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1049976.onnx",
+                "reward": 28.136363636363637,
+                "creation_time": 1735830434.6822584,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1049976.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 15.318181818181818,
-                "creation_time": 1735827119.1914916,
+                "steps": 1099992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1099992.onnx",
+                "reward": 27.476190476190474,
+                "creation_time": 1735830527.6899965,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1099992.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "steps": 1149936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1149936.onnx",
                 "reward": null,
-                "creation_time": 1735827214.8231168,
+                "creation_time": 1735830620.438045,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1149936.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1735827214.919474,
+                "steps": 1199960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1199960.onnx",
+                "reward": 27.795454545454547,
+                "creation_time": 1735830710.7886689,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1199960.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1735827881.4238334,
+                "steps": 1249984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1249984.onnx",
+                "reward": 26.484848484848484,
+                "creation_time": 1735830803.8271983,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1249984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1735827903.7633681,
+                "steps": 1299984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1299984.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1735830898.7846801,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1299984.pt"
+                ]
+            },
+            {
+                "steps": 1349944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1349944.onnx",
+                "reward": 27.181818181818183,
+                "creation_time": 1735830991.918789,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1349944.pt"
+                ]
+            },
+            {
+                "steps": 1399968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1399968.onnx",
+                "reward": 27.581818181818182,
+                "creation_time": 1735831082.3057399,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1399968.pt"
+                ]
+            },
+            {
+                "steps": 1401400,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-1401400.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1735831086.519989,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-1401400.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1735827903.7633681,
+            "steps": 1401400,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 27.545454545454547,
+            "creation_time": 1735831086.519989,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-1401400.pt"
             ]
         }
     },