Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -155.28 +/- 86.76
+      value: -212.65 +/- 129.98
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
 'learning_rate': 0.00025
-'num_envs': 64
+'num_envs': 256
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'ahmadsyy/LunarLander-v2_ppo_scratch'
-'batch_size': 8192
-'minibatch_size': 2048}
+'batch_size': 32768
+'minibatch_size': 8192}
   ```
   

logs/events.out.tfevents.1733212040.c20003bcb990.7493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd428f3da750da954f49c82077e7374c493f8f8dbf00f18526a953a4b32e852c
+size 86653

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248e9175c6f49718bfdfbe6e8226e2e5b70b9c71dd3f10f791a2240b9a3b0a77
-size 42898
+oid sha256:0cfbbf798a671588000dbeb2947dcfd0a7ec9708b39a6796bb85cf191cae80c0
+size 77054

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -155.2766847940215, "std_reward": 86.75708763854689, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T07:45:41.918172"}
+{"env_id": "LunarLander-v2", "mean_reward": -212.65001161909555, "std_reward": 129.98467316287085, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T07:48:15.831449"}