Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -55.84 +/- 57.05
+      value: 23.19 +/- 110.08
       name: mean_reward
       verified: false
 ---
@@ -39,14 +39,14 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 8
+'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -54,9 +54,9 @@ model-index:
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': None
+'target_kl': 0.015
 'repo_id': 'kewangRL/LunarLander-v2'
 'batch_size': 1024
-'minibatch_size': 128}
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1672329814.afca57ec9fc6.38379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785676890f636b2b5334eb84b9784750b01d117784d40b285d0e47932dad0402
+size 624490

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb412b666e32fc1114444c9d4388b6048dad18b0070283b0d2d4734056931a4b
+oid sha256:fd575165a9335b24daf2611b5b4e596666288ce991e89d9290f5768050f7fd98
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -55.84244088424325, "std_reward": 57.053576504567125, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T15:42:25.775398"}
+{"env_id": "LunarLander-v2", "mean_reward": 23.19253075477455, "std_reward": 110.08477590332798, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T16:25:17.490686"}