Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -192.49 +/- 124.42
+      value: -186.58 +/- 109.65
       name: mean_reward
       verified: false
 ---
@@ -33,7 +33,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 500
+'total_timesteps': 50000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1681556551.2373e9397595.4183.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35b0b24ee45f4c4dbd8ba42abfed8284913aa17973d411abd2de54504bda919
+size 44633

model.pt

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

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -192.48962821381954, "std_reward": 124.41960222935549, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T11:02:00.167683"}
+{"env_id": "LunarLander-v2", "mean_reward": -186.578865085489, "std_reward": 109.64844495399402, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T11:03:20.131855"}