Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 77.25 +/- 122.23
+      value: 200.25 +/- 96.98
       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': 0.007
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1718141323.990f15b853ac.4074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e0e7bf0083465ed0624c682c6d1df908f0eb126beb993d3ef465263a17274a
+size 695329

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e88b11cfd220920a1cf7d3958bc5cbebeb346aaf8dd4d8e1a3ee955f088618
+oid sha256:6d89c4e10f1b6d48c1901736b834fea62059339ebe326a7cfe98f94830aa2fd8
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 77.24677784586241, "std_reward": 122.22923940577387, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-11T21:27:33.133681"}
+{"env_id": "LunarLander-v2", "mean_reward": 200.25052764121855, "std_reward": 96.98178524172752, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-11T21:38:29.518837"}