Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -181.93 +/- 107.74
+      value: -47.15 +/- 46.02
       name: mean_reward
       verified: false
 ---
@@ -28,20 +28,17 @@ model-index:
     
   # Hyperparameters
   ```python
-  {'repo_id': 'chgenly/ppo-LunarLander-v2'
-'f': '/root/.local/share/jupyter/runtime/kernel-fc440ec9-4b86-42b3-931f-d1f261eb719a.json'
-'exp_name': 'LunarLander-v2'
-'env_id': 'LunarLander-v2'
-'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+  {'exp_name': 'ppo'
 'seed': 1
-'total_timesteps': 25000
 'torch_deterministic': True
 'cuda': True
 'track': False
-'wandb_project_name': 'ppo-implementation-details'
+'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 150000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -57,6 +54,7 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
+'repo_id': 'chgenly/ppo-LunarLander-v2'
 'batch_size': 512
 'minibatch_size': 128}
   ```

logs/events.out.tfevents.1696278463.038f7278529f.7999.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8399f338d91e543bb88020620a81a52efe99233c7fb3fc2beb1ee851c0b1f3f
+size 302646

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ba6a5bd123aeb8843b34aee2f28818669cfa92ffecbe9b3ed66b9e1ac1a884
+oid sha256:39bad5aad3ef043732732a6b93a3799d7215121a5aeed6da2ba11e7403434a24
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -181.93271356424765, "std_reward": 107.73695105217136, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-02T20:17:53.583664"}
+{"env_id": "LunarLander-v2", "mean_reward": -47.14700270641367, "std_reward": 46.02016177758704, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-02T20:29:57.273328"}