Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -137.73 +/- 66.27
+      value: -178.52 +/- 142.29
       name: mean_reward
       verified: false
 ---
@@ -39,14 +39,14 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 300000
 'learning_rate': 0.00025
-'num_envs': 256
-'num_steps': 64
+'num_envs': 512
+'num_steps': 32
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 8
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1733247522.8835d05a856b.37260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e60f26322171b3a1dad8f14c01524a0528d2dcc2e4e772682ed34e82a419455
+size 74245

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585caad149c9d657681a44ef5d56b802db723d4e5aec2d6cc7d836d15a100ea5
+oid sha256:5446c55f9eb69332cec7e684cba6fce3f84100c26278ac5cb5fa11988845f9f2
 size 59774

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -137.72858234655558, "std_reward": 66.2659821944557, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T17:38:15.843735"}
+{"env_id": "LunarLander-v2", "mean_reward": -178.51857759201573, "std_reward": 142.2928123969609, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T17:40:01.209201"}