Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -161.00 +/- 82.80
+      value: 106.50 +/- 77.64
       name: mean_reward
       verified: false
 ---
@@ -38,19 +38,19 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
-'learning_rate': 5e-05
+'learning_rate': 0.001
 'num_envs': 8
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.999
+'gamma': 0.994
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.015
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1684162759.5fc12f631080.29869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8ef70bb7928840d198430f7a90f67304e93ba7419399216b717ca7de05468b
+size 126257

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e439732e434cb3fea8453b99a9fd6e1309280e872c8123d360876d6ad0b3c2d3
+oid sha256:0146ddbd7147b20b906ba971175a2b08e1125f3306def800a376865fdb6276e6
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -161.00468558009493, "std_reward": 82.79826320590251, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T14:57:53.143272"}
+{"env_id": "LunarLander-v2", "mean_reward": 106.50124481135063, "std_reward": 77.64316630977838, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T15:07:21.358152"}