Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.79 +/- 78.99
+      value: -162.88 +/- 78.93
       name: mean_reward
       verified: false
 ---
@@ -38,25 +38,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'total_timesteps': 1000000
+'learning_rate': 0.000125
+'num_envs': 16
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 8
+'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.4
 'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
+'ent_coef': 0.03
+'vf_coef': 0.6
+'max_grad_norm': 0.4
 'target_kl': None
 'repo_id': 'pm390/LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1662324684.624f3f3c0672.728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0937251530d8068e200b4a93dab94b59dd750577916f2fc6fced8147c29f6af6
+size 125018

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40e04bf2b6121fa3344974ae4fe959f9f08a5d324c3f75a801c9ad9df763af4
+oid sha256:06deccbb7adc999536f3496e49815e9b1fad596f4988072376b1b7a751894178
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.78854956623383, "std_reward": 78.9862128665021, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T20:48:23.275011"}
+{"env_id": "LunarLander-v2", "mean_reward": -162.88328449226753, "std_reward": 78.92687312975224, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T20:52:40.675612"}