Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -76.58 +/- 85.01
+      value: 154.18 +/- 60.71
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
-'learning_rate': 0.0015
-'num_envs': 4
-'num_steps': 128
+'total_timesteps': 1000000
+'learning_rate': 0.0003
+'num_envs': 8
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 32
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
-'clip_vloss': False
+'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'wilt8/ppo-CleanRL-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 8192
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1725432341.coder-william-william-gpu-dev-01-7657b6479b-wgphg.29180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2a7f35b8da2a636b5fb61104c5e3324cf8413fd450a7aa53b30f11060c1bea2
+size 297006

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb414d0156e976e07fbb0f4a362aeb6d9d142fc763a1edb85c0accd04d3159c
+oid sha256:89df913c6eb7ac01753e2baab1da7eb973d09e8e0578a8af0bd9c7e35958a368
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -76.58254711071329, "std_reward": 85.01030913255534, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:30:24.404585"}
+{"env_id": "LunarLander-v2", "mean_reward": 154.1754895882536, "std_reward": 60.70603583112726, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T15:00:23.119032"}