Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -53.67 +/- 78.29
+      value: -58.00 +/- 22.77
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': 'KeWangRL'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.00015
 'num_envs': 16
 'num_steps': 128

logs/events.out.tfevents.1672324903.afca57ec9fc6.18747.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1792ea9719245e7c1e84f3857960782ebbcbb3a278053ab42ad27d9b05cbfb
+size 474416

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e485a5e4cb8666b627be33ad6fb214394db80f99bcd5131ac26417d3dcbaa161
+oid sha256:ea0211caf52baab10d26fe15c03c49b448891699bf19c37190f5e2fd732883c1
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -53.666972897583456, "std_reward": 78.28967729124854, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T14:40:00.547563"}
+{"env_id": "LunarLander-v2", "mean_reward": -58.00304377871121, "std_reward": 22.773402729020425, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T14:58:26.105058"}