Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 122.22 +/- 117.84
+      value: -62.91 +/- 60.76
       name: mean_reward
       verified: false
 ---
@@ -39,23 +39,23 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
 'learning_rate': 0.01
-'num_envs': 4
-'num_steps': 256
+'num_envs': 8
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 8
+'update_epochs': 2
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.001
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'sw32-seo/ppo-LunarLander-v2'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 4096
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1681396566.a91220c61ac6.6630.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12ac00220740ef52d7005dfbfe086f30a8b93c7ca093cf29bb62e58e50cff90
+size 110178

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b36b1505815dae7d9c9b3a0e923d24e979a3fd13461d0e69faee9cbef343e51
-size 145257
+oid sha256:58daa9eb0c2a0d70f1aff455a16036660ada92de8381df4a60cda071724cf4ff
+size 76753

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 122.216761872768, "std_reward": 117.84090456705555, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-13T14:26:24.661665"}
+{"env_id": "LunarLander-v2", "mean_reward": -62.90837575158006, "std_reward": 60.755954084492984, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-13T14:37:10.103604"}