Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.05 +/- 83.69
+      value: -61.85 +/- 68.90
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 150000
+'total_timesteps': 250000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1673509292.fbb46569ee42.21956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000dfe2b27c51547c2f5c6b99aee5e428d8d0148fc0f55d93f9e3d595feec14c
+size 251708

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4b8526da025cd58ba32700e5c596e8f27dd3b4c11e513e22c8f8ecdf444076
+oid sha256:a76f985aa102fdd821cf7ec27d291e5cf8ff805b91dcd9425e56e27b65b33698
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.05263953938382, "std_reward": 83.69325637381145, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:40:07.395295"}
+{"env_id": "LunarLander-v2", "mean_reward": -61.845203775428374, "std_reward": 68.89759545254032, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:45:30.978685"}