Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -110.99 +/- 83.90
+      value: -123.35 +/- 105.55
       name: mean_reward
       verified: false
 ---
@@ -38,24 +38,24 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 3e-05
+'learning_rate': 0.0002
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 32
+'num_minibatches': 64
+'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.01
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yuval6967/LunarLander-v2PPO'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1685096636.2850cb3f29b2.32056.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2869d273aa2e8f920d50bb12e4f115cce9da117465195b69e26e128ceff1e4c9
+size 64089

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7664452e77700ed1e8b1bdf813951628ec5060ca55323a4d0d6286c7ab12c3d
+oid sha256:a14df6e5d78a5004f0af6fe34a80ec81fae444a591b3ebc61167c7b41e7a9f01
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -110.98683783991169, "std_reward": 83.9005254490006, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:14:20.490003"}
+{"env_id": "LunarLander-v2", "mean_reward": -123.3530471352419, "std_reward": 105.55354602930377, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T10:24:44.333396"}