Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 169.67 +/- 97.97
+      value: 19.23 +/- 124.79
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 1000000
+'total_timesteps': 500000
 'torch_deterministic': True
 'cuda': True
 'track': True
@@ -40,22 +40,22 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'num_envs': 16
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 16
+'num_minibatches': 16
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.005
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': 0.015
 'repo_id': 'HuggingMachines/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 4096
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1766355148.n-62-12-19.3111337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24638ecc04a657fc515a63b3d9a7eca7efe39a718d0c98f961dbeeb44078a13a
+size 16444588

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c370fb780d7e023a029eef013dc7419127ab245aeeb0c16da65f09f337351ab8
+oid sha256:cde648522b5209bfe567367feb73595d21036a789cd8adc01022c18c1ee4dc84
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 169.67474608802868, "std_reward": 97.96587262215958, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-18T22:44:27.773292"}
+{"env_id": "LunarLander-v2", "mean_reward": 19.23149751919279, "std_reward": 124.79134922588452, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-22T00:45:21.959342"}