Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -184.90 +/- 117.55
+      value: -124.93 +/- 83.02
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1727599605.50c4b48e3dc0.9713.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807c5c2a186bacd69d37a75abc0a899a80ea14676ed9298e3612912edcc8280f
+size 221325

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85946e39dbf3f8be596cf7e6903436fdff2fe0916bbae2c8bc7963d99fdb68a5
+oid sha256:da85c2655fa22eceb08f285bb6687b81436a7f944348338edb35256ae558b6fb
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -184.89682920296508, "std_reward": 117.54843720035201, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T08:44:04.344929"}
+{"env_id": "LunarLander-v2", "mean_reward": -124.9275477196552, "std_reward": 83.02110562522213, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-29T08:48:04.356107"}