Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 23.19 +/- 110.08
+      value: 15.03 +/- 87.72
       name: mean_reward
       verified: false
 ---
@@ -39,9 +39,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.0003
-'num_envs': 4
-'num_steps': 256
+'learning_rate': 0.00035
+'num_envs': 8
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -51,7 +51,7 @@ model-index:
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.015
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': 0.015

logs/events.out.tfevents.1672332064.afca57ec9fc6.47445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c70ed1ab68008256641e6f83790e5a43d19a9edd27ec6b11c799eaddecb087
+size 627391

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd575165a9335b24daf2611b5b4e596666288ce991e89d9290f5768050f7fd98
+oid sha256:48f61259aa386f79da36587e94a814a2e68a182aca67f851683783ba07355514
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 23.19253075477455, "std_reward": 110.08477590332798, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T16:25:17.490686"}
+{"env_id": "LunarLander-v2", "mean_reward": 15.034289768214922, "std_reward": 87.72029334186728, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T17:01:25.428723"}