Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -51.65 +/- 42.44
+      value: 69.31 +/- 92.69
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 500000
 'learning_rate': 0.00025
-'num_envs': 16
+'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Terence3927/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1668324692.terence-rl-2-0.197512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855be523c5642a7774c5ca71820ef8db99273fe1cc3621cfbde2bd978a64b84c
+size 668266

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41b8612b30fb22f4c93e0523b8eef1303cb96d6c981747a5b3f111bbea28844
+oid sha256:8c02fdb934d04de10030fa2110a194cb779edbfd25ed74f8576d3a89d3b76231
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -51.646336549214276, "std_reward": 42.4377542963733, "n_evaluation_episodes": 10, "eval_datetime": "2022-11-13T07:29:56.611680"}
+{"env_id": "LunarLander-v2", "mean_reward": 69.30578168884627, "std_reward": 92.69194556044238, "n_evaluation_episodes": 10, "eval_datetime": "2022-11-13T07:46:22.529645"}