Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -136.93 +/- 54.21
+      value: 70.12 +/- 65.81
       name: mean_reward
       verified: false
 ---
@@ -37,25 +37,25 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 500000
+'learning_rate': 0.002
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.001
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'PaulTbbr/ppo-LunarLander-v2-u8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1711900794.dcbb53a8808a.11169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5360e46f32f6df9cfb22cf9e1723ce504483646e3fa982801af9ca746cd0d76
+size 183243

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:d493c0ebfdd299142323494d8206f32966de48d1f1b3b5db0029ca55e93c7cfc
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -136.93196333763706, "std_reward": 54.21257241554637, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-31T15:34:09.312176"}
+{"env_id": "LunarLander-v2", "mean_reward": 70.12390958673609, "std_reward": 65.80544568502333, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-31T16:13:21.550247"}