Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -43.36 +/- 15.81
+      value: 179.83 +/- 105.87
       name: mean_reward
       verified: false
 ---
@@ -37,18 +37,18 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
-'learning_rate': 0.00025
+'total_timesteps': 1000000
+'learning_rate': 0.0005
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.3
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'eseskay/ppo-LunarLander-v2-unit8-p1'
 'batch_size': 512
-'minibatch_size': 128}
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1721256096.04213d94c9ce.25613.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bf28919321a2628a1f9924d111e7e9dc3800b27f54f7a5752f781717abf698
+size 1416499

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77ef9c75a6010d53b638b2fbf6a0a2a078997ab1d6d29a1b7ff740ac1d0c4bf
+oid sha256:fb1f785b876fcc9a407ed6f6a42aae5521aa8df41ae05a44c428cf02a80f5d05
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -43.35649323305557, "std_reward": 15.810750245442385, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-17T22:24:02.921016"}
+{"env_id": "LunarLander-v2", "mean_reward": 179.82501217024523, "std_reward": 105.87364983885976, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-17T23:12:30.019121"}