Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -42.12 +/- 20.51
+      value: -146.05 +/- 83.69
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 300000
+'total_timesteps': 150000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1673509082.fbb46569ee42.21049.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc9d62e3f57b6094606901a1694900c04f0586c0ef616ebb54744dee35f67e7
+size 150768

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e1a614afc4af4423bef5607f4551ff1bc44112aa9db423ddd9291023155459
+oid sha256:ef4b8526da025cd58ba32700e5c596e8f27dd3b4c11e513e22c8f8ecdf444076
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -42.11552959973237, "std_reward": 20.505771574036753, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:35:26.402292"}
+{"env_id": "LunarLander-v2", "mean_reward": -146.05263953938382, "std_reward": 83.69325637381145, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-12T07:40:07.395295"}