Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -190.74 +/- 114.43
+      value: -179.59 +/- 78.17
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 100000
+'learning_rate': 5e-05
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -52,10 +52,10 @@ model-index:
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
+'max_grad_norm': 0.3
+'target_kl': 0.02
 'repo_id': 'Brain33/ppo-LunarLander-v2_Unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1754154655.b370af870f20.6471.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808bae116c86b333436f17dad356d8d6bda865fda9cd255725ab412e8c4c44b1
+size 179172

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+oid sha256:ef3283559bb0e31cefdae63f35559a5b6e03829e5cef351351699cea08bb309c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -190.7434212957234, "std_reward": 114.43039190639524, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-02T17:04:23.706188"}
+{"env_id": "LunarLander-v2", "mean_reward": -179.58848022343477, "std_reward": 78.16953941918148, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-02T17:12:06.364116"}