Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -111.74 +/- 74.80
+      value: 6.99 +/- 50.95
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1673508092.fbb46569ee42.16879.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091c35a72d2322ffba57cf0bd60a0801adb2af6c95fe8a5bed94dfe43c7d2f06
+size 201238

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f529fff64cd38081c337cbf1b9941a2d289111f6a5dac72c20fb74c059df6d14
+oid sha256:ac5d3852fefd8a2962aab5c649ac0d8eb5a091d65f26bb882970c15f4f369887
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -111.73770606635796, "std_reward": 74.80103687143192, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:18:30.783098"}
+{"env_id": "LunarLander-v2", "mean_reward": 6.98734131264342, "std_reward": 50.948523594527984, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:24:34.581160"}