Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
  type: LunarLander-v2
  metrics:
  - type: mean_reward
- value: -221.14 +/- 170.03
+ value: -198.93 +/- 138.92
  name: mean_reward
  verified: false
 ---
@@ -38,15 +38,15 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.0001
+'learning_rate': 1e-05
 'num_envs': 4
-'num_steps': 256
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 8
-'update_epochs': 6
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'arhamk/ppo-LunarLander-v2-2'
-'batch_size': 1024
-'minibatch_size': 128}
+'batch_size': 8192
+'minibatch_size': 1024}
  ```
  

logs/events.out.tfevents.1718025239.887b5cfc0142.11575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6080a4216017af3fe831b9c3b11759a46b1153aaf3fab6762c2d9be3087b442e
+size 68568

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c03d26812b5698b0e80f322107916a141fd17c54e3616b37ed86dfafba499c2
+oid sha256:fbdda57fcf2dccebfd2e45a58ccf4fcfd5c9b9049649eb63e9b4aeaac316fa57
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -221.13670925092933, "std_reward": 170.03142679682054, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:11:05.131029"}
+{"env_id": "LunarLander-v2", "mean_reward": -198.92899401262682, "std_reward": 138.91576028315262, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:14:39.301212"}