Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 107.60 +/- 82.60
+      value: 169.67 +/- 97.97
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 150000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': True
@@ -46,14 +46,14 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 16
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': None
+'target_kl': 0.015
 'repo_id': 'HuggingMachines/ppo-LunarLander-v2'
 'batch_size': 2048
 'minibatch_size': 512}

logs/events.out.tfevents.1766089074.n-62-20-1.2710435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5b9044a3fc004bfd355fcf78628c3e6dbfc228c27a1d1b1acdcddf34eef4f5
+size 32446110

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be82b199a2488e6d0f84f05ee8ead90f3b6b0a51b6999219f447fb3a4d55e50b
+oid sha256:c370fb780d7e023a029eef013dc7419127ab245aeeb0c16da65f09f337351ab8
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 107.60335285911106, "std_reward": 82.60173839158603, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-18T21:09:35.797300"}
+{"env_id": "LunarLander-v2", "mean_reward": 169.67474608802868, "std_reward": 97.96587262215958, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-18T22:44:27.773292"}