Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -158.01 +/- 38.12
+      value: 29.26 +/- 109.69
       name: mean_reward
       verified: false
 ---
@@ -38,25 +38,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.000125
-'num_envs': 16
-'num_steps': 256
+'total_timesteps': 1000000
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 8
-'update_epochs': 8
+'num_minibatches': 4
+'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.4
+'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.03
-'vf_coef': 0.6
-'max_grad_norm': 0.4
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'pm390/LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 512}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1662325096.624f3f3c0672.832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a58b5462717aecde1151bd7700f0b2976991f89613454bed9859befa1a7c30b
+size 1006194

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3620316316206e30f94908b79f24d4d44a5cd8bddd109b78046e447f1fc0bf2
+oid sha256:22c6a2ee66a04c7a7faf6bb1a94f7cf59bd363baf1fa860acd583ab5e7432c11
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -158.00572748657743, "std_reward": 38.122258531643375, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T20:55:26.211208"}
+{"env_id": "LunarLander-v2", "mean_reward": 29.26223853143456, "std_reward": 109.6868501357021, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T21:21:13.177374"}