Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.59 +/- 78.17
+      value: -138.28 +/- 70.86
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 5e-05
+'total_timesteps': 1000000
+'learning_rate': 2e-05
 'num_envs': 4
 'num_steps': 256
 'anneal_lr': True
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 6
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1754154877.b370af870f20.7459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67caba190489958bfb1e1639d3747e2d7464bb04d30357405bfff8f1a36e5140
+size 1492666

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef3283559bb0e31cefdae63f35559a5b6e03829e5cef351351699cea08bb309c
+oid sha256:5638a67bd58ed659a8820a0a33c57c1ceeb5f8e078d2c65ce8acd5608d160ee8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.58848022343477, "std_reward": 78.16953941918148, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-02T17:12:06.364116"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.27553285365906, "std_reward": 70.8642467799207, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-02T17:27:33.355159"}