Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -56.03 +/- 125.24
+      value: -92.45 +/- 79.72
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.0025
+'learning_rate': 0.01
 'num_envs': 4
-'num_steps': 128
+'num_steps': 300
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'caioiglesias/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1200
+'minibatch_size': 300}
   ```
   

logs/events.out.tfevents.1677778804.6c4e5c51f044.8674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf6bb60643589b65bd065e03ead8925e6f798455e0f32ffacd320d74a711948
+size 62379

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1130dbc2ea11f45242bc9a621ee3ac7e899b7b6bdd6c8ba053f363e2aa898e9c
+oid sha256:8081c85a814ceaa0645287c738122fdd0b47ad40edd66adf5777c71b32550bee
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -56.027738569870735, "std_reward": 125.2436025369509, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:34:03.226720"}
+{"env_id": "LunarLander-v2", "mean_reward": -92.44806132550572, "std_reward": 79.7219557687308, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:41:01.839171"}