Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -74.81 +/- 75.57
+      value: -59.04 +/- 65.01
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.0009
-'num_envs': 4
-'num_steps': 64
+'num_envs': 8
+'num_steps': 32
 'anneal_lr': True
 'gae': True
 'gamma': 0.999

logs/events.out.tfevents.1707494120.a74decb87bc7.7751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db6f5e78f37fbdd237fe65bee76dea768e47b5d1b8f87b0c7bd118589124de7
+size 129647

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aaf599608c5b138a6c7fd95c163f0886f8a300a603cbddd5b2a041a7fae5f20
+oid sha256:e21635d909f051fcea0c17dc3ac5aac00f18a22af2242c18678b092848097393
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -74.81047080368151, "std_reward": 75.56735594655072, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:54:22.811353"}
+{"env_id": "LunarLander-v2", "mean_reward": -59.03522093417784, "std_reward": 65.0056719155476, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:56:19.639774"}