Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -178.47 +/- 76.52
+      value: -217.44 +/- 126.66
       name: mean_reward
       verified: false
 ---
@@ -33,7 +33,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 500
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -55,9 +55,8 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'push_to_hf': True
+'repo_id': 'jmurphy97/LunarLander-v2'
 'batch_size': 512
-'minibatch_size': 128
-'repo_id': 'jmurphy97/LunarLander-v2'}
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1681556343.2373e9397595.3259.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c5272cca0ddb769a5480e41f1d5d3d22f6c26e95844e95c51764bd721d66e4
+size 726

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcf78178ab033a93b34f7326d70cc42208f7483f1f35803a03aad5050e0f842
+oid sha256:9d415ace67605d0e4d171521ebcb0c7fcb2053e5d8fef4373af078321b4f6b4a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -178.47413384098817, "std_reward": 76.51928048683259, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T10:53:55.091416"}
+{"env_id": "LunarLander-v2", "mean_reward": -217.43773267589532, "std_reward": 126.65769659188194, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T10:59:08.918246"}