Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -88.37 +/- 36.25
+      value: 125.91 +/- 22.40
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1727002927.fa36c63a5d52.15943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245a95256e0a591e2aeafef93208e8ce0fb849e7dc1cd6446a6f8d7f184648b3
+size 345088

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b1588a87247e02f5eef0468109f0e1a4fb7190be6d3c6c69f6eef8e2199912
+oid sha256:2e99814bac607aa07751e7e8f7ee27f84ba6790665053ab2249f43b3213595f8
 size 147730

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -88.3738041112943, "std_reward": 36.24991057245153, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-22T10:54:33.984058"}
+{"env_id": "LunarLander-v2", "mean_reward": 125.91100452258372, "std_reward": 22.400778846907304, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-22T11:23:49.234443"}