Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 79.47 +/- 57.46
+      value: 251.74 +/- 17.34
       name: mean_reward
       verified: false
 ---
@@ -36,17 +36,17 @@ model-index:
 'v_hidden_layers': (64
 64)
 'learning_rate': 0.0003
-'anneal_lr': True
+'anneal_lr': False
 'total_timesteps': 1000000
 'num_steps': 1024
 'gamma': 0.999
 'gae_lambda': 0.98
 'num_minibatches': 256
 'num_epochs': 4
-'norm_advantage': True
+'norm_advantage': False
 'clip_coef': 0.2
-'clip_vloss': True
-'vf_coef': 0.5
+'clip_vloss': False
+'vf_coef': 1.0
 'ent_coef': 0.01
 'max_grad_norm': 0.5
 'target_kl': None}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d237aadc03c4a69843d7bc5a7747d7777ab439ef09288af720bfe5fadc0ee2c5
-size 42597
+oid sha256:6fe0a49b95f74372f08d613ddac14b88d73d1ae1e273594c15c0a55cdfa5d17d
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 79.46508621838886, "std_reward": 57.46079809014783, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T01:15:29.426508"}
+{"env_id": "LunarLander-v2", "mean_reward": 251.73706333353397, "std_reward": 17.340777616865214, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T12:44:54.661323"}