Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.91 +/- 63.78
+      value: 31.26 +/- 57.03
       name: mean_reward
       verified: false
 ---
@@ -28,7 +28,7 @@ model-index:
     
   # Hyperparameters
   ```python
-  {'exp_name': 'ppo'
+  {'exp_name': 'ppo2'
 'seed': 1
 'torch_deterministic': True
 'cuda': True
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680459976.d34a81756552.30237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89395c6a233a320b7f4ca79cc563b23ac9a7a8bd793a05ed6a82e18f7dee3641
+size 675874

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d7840a5f0ff67e368ad7fa468279ae6d6aaacda10d8feccce2d1ebb22e2630
+oid sha256:389208e83d3830e2a880958a659b5370f282ed949f20a39702be07d628ebbd32
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.91044646293763, "std_reward": 63.78046084391993, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T18:04:24.693260"}
+{"env_id": "LunarLander-v2", "mean_reward": 31.26296963046452, "std_reward": 57.03363927687003, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T18:40:58.235721"}