Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -105.44 +/- 50.76
+      value: -10.97 +/- 59.31
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1692004184.c14e1bfbd2c3.7657.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7700d5fb9cf81105af9a71791f65a8c940a9139c94540926e3fead7fd9706e32
+size 724455

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2cf23fc51e572a20f11bd05aaf450dd266749f9e5838c57f07c340fa0d4b33
+oid sha256:ba3bfc6accd9b3ad96a3109eeb65628ef460b5d85ae561451579bafda7bd2c5f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -105.43591761371226, "std_reward": 50.76115627569614, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:07:25.451342"}
+{"env_id": "LunarLander-v2", "mean_reward": -10.966958893174622, "std_reward": 59.3086053918031, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-14T09:22:10.491180"}