Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -104.81 +/- 79.23
+      value: -47.05 +/- 36.85
       name: mean_reward
       verified: false
 ---
@@ -37,15 +37,15 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 16
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 16
 'update_epochs': 16
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'lbaeriswyl/ppo-self-implement-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 4096
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1712266064.81c9e6ad124a.5187.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111d290f3a13511cf9ee2bc0a67246ca4ed5322f02ff14fe77d330ea64cfdead
+size 71436

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097630b106a9af7ef1e301d224f9b55fc86c4e195c6ffb2ed6a389215397f16c
+oid sha256:b68f72a819aedb9256c5696efbc84f24039061d21f829ddb439f6682a4b8aaf2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -104.80652058908933, "std_reward": 79.2339695071753, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-04T21:25:14.757080"}
+{"env_id": "LunarLander-v2", "mean_reward": -47.04632264289144, "std_reward": 36.84505280958405, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-04T21:29:21.872917"}