Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -165.42 +/- 87.81
+      value: -131.44 +/- 59.79
       name: mean_reward
       verified: false
 ---
@@ -40,22 +40,22 @@ model-index:
 'total_timesteps': 100000
 'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 512
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 16
-'update_epochs': 4
+'update_epochs': 8
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.05
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'slava-medvedev/unit8-ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1698341855.e81c8261624b.8111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c06b6d800b38ac28a680197b9e326febf8c6d0fa2729ac48e6f16bd1643bbe
+size 124351

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb6cc3387513b86dd00f99107ded15b8a12bc7e82a379ce58ddaa3171264817
+oid sha256:183fc86459f936728dfa1a06eae1496110f4a7fc02d4aface727c685c7dcdd8f
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -165.41621621730934, "std_reward": 87.80982473819368, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:36:55.054333"}
+{"env_id": "LunarLander-v2", "mean_reward": -131.44013028093292, "std_reward": 59.79377215983551, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:39:01.347514"}