Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -154.66 +/- 91.75
+      value: -149.62 +/- 69.77
       name: mean_reward
       verified: false
 ---
@@ -43,14 +43,14 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
+'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 5
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.5
+'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1698071542.527fe3665085.20642.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:723af5cb91ba18c6e9365a50e94c47f7ca2222880de5be35e085936b21c64c05
+size 874206

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67e935f7993924b75fa144025f8aeaf9dabf4d467736b3373ed5da14782f77e
+oid sha256:7b1d5295d0f0a75b98170f907a71cb16c194d86cc49afd079f10c4ee8776f427
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -154.65525397827173, "std_reward": 91.74715553996019, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:31:12.787699"}
+{"env_id": "LunarLander-v2", "mean_reward": -149.62111145713575, "std_reward": 69.77237910656221, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:36:56.923918"}