Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -172.78 +/- 101.91
+      value: -140.37 +/- 96.35
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 3e-05
+'learning_rate': 0.001
 'num_envs': 16
 'num_steps': 512
 'anneal_lr': True
@@ -50,7 +50,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.05
 'clip_vloss': True
-'ent_coef': 0.1
+'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1685094034.2850cb3f29b2.19981.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f624f8887f5fd019c8c5d41b29699a05e4a32fc16780b0491035ffc7266c3aed
+size 61784

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87ef4e33a23dfdd524d8209675a10385ebcc8d0bf111c2a07e98ebae787b723
+oid sha256:4ffa03898b244e0e5c96f71882cdc3d8ae5c36348d50d442f8fb0bf75d7795f7
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -172.77634604822197, "std_reward": 101.9078990771665, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:40:10.907722"}
+{"env_id": "LunarLander-v2", "mean_reward": -140.37309354706989, "std_reward": 96.34637960793312, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T09:40:55.428676"}