Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -196.61 +/- 138.41
+      value: -63.02 +/- 94.35
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1721089044.03605870ec63.17487.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59965c9745ec21b0e424ef7d5e3559c88aef0172b18c7c490dd3aeed93bd81ff
+size 675363

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -196.61058157043198, "std_reward": 138.40678036426954, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-16T00:16:03.028894"}
+{"env_id": "LunarLander-v2", "mean_reward": -63.02371296296, "std_reward": 94.35105121211205, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-16T00:31:44.713585"}