Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -58.00 +/- 22.77
+      value: -55.84 +/- 57.05
       name: mean_reward
       verified: false
 ---
@@ -39,14 +39,14 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.00015
-'num_envs': 16
-'num_steps': 128
+'learning_rate': 0.00025
+'num_envs': 4
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'kewangRL/LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 1024
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1672327184.afca57ec9fc6.27873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee3f423a5a892303b2ca8376ea0a22d35d593ec31c76a591667b60960ae2dc9
+size 614872

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0211caf52baab10d26fe15c03c49b448891699bf19c37190f5e2fd732883c1
+oid sha256:fb412b666e32fc1114444c9d4388b6048dad18b0070283b0d2d4734056931a4b
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -58.00304377871121, "std_reward": 22.773402729020425, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T14:58:26.105058"}
+{"env_id": "LunarLander-v2", "mean_reward": -55.84244088424325, "std_reward": 57.053576504567125, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T15:42:25.775398"}