Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 79.33 +/- 56.38
+      value: -53.67 +/- 78.29
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
-'num_envs': 4
+'learning_rate': 0.00015
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'kewangRL/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1672324567.afca57ec9fc6.17344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7019ae9c3f344adabe041f8adc77b8c1afaee8bba0a0818dd1bf4d4a6595f9
+size 328851

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:646d001cd237b319ee5883847d0dec4ce904242e3476b4f55a6a9ac98b535cd4
+oid sha256:e485a5e4cb8666b627be33ad6fb214394db80f99bcd5131ac26417d3dcbaa161
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 79.32771514240426, "std_reward": 56.38185000331535, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T14:34:08.573633"}
+{"env_id": "LunarLander-v2", "mean_reward": -53.666972897583456, "std_reward": 78.28967729124854, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-29T14:40:00.547563"}