Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 19.23 +/- 124.79
+      value: -20.83 +/- 29.21
       name: mean_reward
       verified: false
 ---
@@ -32,14 +32,14 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': True
 'wandb_project_name': 'ppo-implementation-details'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 16
+'num_envs': 20
 'num_steps': 256
 'anneal_lr': True
 'gae': True
@@ -48,14 +48,14 @@ model-index:
 'num_minibatches': 16
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.15
 'clip_vloss': True
 'ent_coef': 0.005
 'vf_coef': 0.5
 'max_grad_norm': 0.5
-'target_kl': 0.015
+'target_kl': None
 'repo_id': 'HuggingMachines/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 256}
+'batch_size': 5120
+'minibatch_size': 320}
   ```
   

logs/events.out.tfevents.1766918445.n-62-12-19.3451480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a12f5d637ed4be7d861cbb80e4176701f2c299ec4c029886437c148ec2bc21
+size 26424094

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde648522b5209bfe567367feb73595d21036a789cd8adc01022c18c1ee4dc84
+oid sha256:83d32c0a7ea90bf86812adfad521f295e5acecfe73dec2e279b274df7ae37bcf
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 19.23149751919279, "std_reward": 124.79134922588452, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-22T00:45:21.959342"}
+{"env_id": "LunarLander-v2", "mean_reward": -20.826285796424994, "std_reward": 29.212473757643334, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-28T16:24:17.806546"}