Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -215.05 +/- 111.85
+      value: -158.33 +/- 72.91
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 256
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.998
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'dussinus/ppo-cleanrl-Lunar'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1682412743.66a7c698a397.10843.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ef202dc2fc79c6e5689159a2206af2eae74683a3a34636c033a0b511bf0b3c
+size 145596

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:99baf3f48be2a8db27ffc82980f5b9f1c74838722440b4c1d97bc158993c05f2
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -215.0485521525256, "std_reward": 111.8467191969054, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-25T08:45:24.867120"}
+{"env_id": "LunarLander-v2", "mean_reward": -158.32640706507982, "std_reward": 72.90675165091433, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-25T08:53:17.157050"}