Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -152.74 +/- 84.73
+      value: -111.96 +/- 88.86
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 0.003
 'num_envs': 16
-'num_steps': 512
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.98
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'arhamk/ppo-LunarLander-v2-2'
-'batch_size': 8192
-'minibatch_size': 2048}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1718027627.887b5cfc0142.21900.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05a3c32858ac64aa7707e32752873fe4cbba3fc7d26ccda8ce06bc1f0cbd09a
+size 44480

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fde366c21ba857b4d72d3585861c9117291e86520d76f8f06c228af447d672
+oid sha256:49eb8f2da74322a0bbd6e7f6d60747ac0c75a7aa5aa690d355caf86caf7a9358
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -152.73663127235886, "std_reward": 84.73478627695557, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:52:38.801540"}
+{"env_id": "LunarLander-v2", "mean_reward": -111.96160298495883, "std_reward": 88.85799312742037, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:54:26.604742"}