Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 185.90 +/- 102.99
+      value: 108.59 +/- 36.39
       name: mean_reward
       verified: false
 ---
@@ -37,15 +37,15 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 256
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -54,8 +54,9 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
+'f': None
 'repo_id': 'patonw/cleanppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1692247472.muon.52928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b983c822ea322c5a9ed0e3ceb48b114bc78abcd8e613009d6d3e7c7f06882d5c
+size 327667

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8e1483845d46f5eeeca4350da0c655ef791ad3492cc3b85efe563f1fddee1e
+oid sha256:5fcb85f238151bc971b999f9593aa995bd38c7834087fb3cc33cd2b65376ef6c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 185.89920698828374, "std_reward": 102.98591994480977, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T17:22:57.588901"}
+{"env_id": "LunarLander-v2", "mean_reward": 108.59351659990284, "std_reward": 36.385255295169046, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T21:49:26.937037"}