Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 95.16 +/- 78.54
+      value: -76.58 +/- 85.01
       name: mean_reward
       verified: false
 ---
@@ -35,10 +35,10 @@ model-index:
 'track': False
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
-'capture_video': True
+'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
-'learning_rate': 0.0025
+'learning_rate': 0.0015
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -49,8 +49,8 @@ model-index:
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.05
+'clip_vloss': False
+'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1725427579.coder-william-william-gpu-dev-01-5fd55f9c84-plnfx.1654663.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf2ff4d6a4f02f00b303c38950f11623a83b6ae558f17671d189dad3a07f76b
+size 315272

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f41b859b1a2b4c8dc4f7e12f36de7eaf2cef2576168c4e002ceeb64505cbfff
+oid sha256:afb414d0156e976e07fbb0f4a362aeb6d9d142fc763a1edb85c0accd04d3159c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 95.15691743880595, "std_reward": 78.53641972479562, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:25:34.947775"}
+{"env_id": "LunarLander-v2", "mean_reward": -76.58254711071329, "std_reward": 85.01030913255534, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:30:24.404585"}