Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -121.56 +/- 14.74
+      value: -134.94 +/- 69.69
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
+'gamma': 1.02
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1703596613.cybertron.1745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c957f535bcd59ec9dc9c5171d1354dacb5c19b6c3490dcf48e54b5c80bcd4a
+size 110093

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb1c8ae9e363c8b45a0ea950d0c91e82cefbb0fe3d5d36668e8902fed87eea5
+oid sha256:e868488144d8cf2fec4ab7315faf748edc5f266f057701efadd92536376a98bc
 size 672534

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -121.55896973720397, "std_reward": 14.741084119426633, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:15:37.396587"}
+{"env_id": "LunarLander-v2", "mean_reward": -134.93791757388504, "std_reward": 69.68858360606443, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:17:26.452827"}