Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -255.25 +/- 155.79
+      value: -104.18 +/- 83.56
       name: mean_reward
       verified: false
 ---
@@ -31,14 +31,14 @@ model-index:
   {'exp_name': 'ppo'
 'seed': 1
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'target_kl': None
 'max_grad_norm': 0.5
 'vf_coef': 0.5
 'ent_coef': 0.01
 'clip_coef': 0.2
 'clip_vloss': True
-'num_steps': 64
+'num_steps': 128
 'learning_rate': 0.00025
 'gae': True
 'gamma': 0.99

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6faef87fa309c1fb57692cdf3d94581161a87cbabd14f521a0ef7543c4821de5
+oid sha256:f4f0bc0f1503a07837560199df54821ffc0e0a4e66cafdfeaa50612bad3296e9
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -255.24609862177644, "std_reward": 155.79148122799913, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T16:16:30.596117"}
+{"env_id": "LunarLander-v2", "mean_reward": -104.1814593575411, "std_reward": 83.55580372276808, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T16:19:24.156573"}