Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -172.06 +/- 53.62
+      value: -207.69 +/- 124.63
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 5e-05
+'learning_rate': 0.00015
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -51,7 +51,7 @@ model-index:
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.005
-'vf_coef': 0.5
+'vf_coef': 0.25
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'earlzero/LunarLander-CleanRL'

logs/events.out.tfevents.1735411274.2763f7ab14bb.6906.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3786fb1d0793c1f8e994e2a65aa292584a754a09eaa437a3c10268de508b605
+size 110956

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc157e267c097626f32c6fc37e62b49ef307a0f59ac90936d5e7b07619fc461b
+oid sha256:7fe5a7b2340829c1b23be89b5c729656f821090a3b41dca4167f98ffe43a1458
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -172.06075819909432, "std_reward": 53.61607685641903, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:39:13.830362"}
+{"env_id": "LunarLander-v2", "mean_reward": -207.68645655597902, "std_reward": 124.6328090942577, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:41:57.958113"}