Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -106.91 +/- 43.63
+      value: -58.68 +/- 70.13
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1667210795.35d33fc0db11.685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b3b3a5ad0d7d86a782386fceb505c7bfb69add7ecc16be2faa1be435acd58a0
+size 201269

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:213bac8bad39cb373c9f15f510ce983e1d668432ce741b493d008f8508a1b89f
+oid sha256:709cbe1fa1edc22d85af7255f8c0b3471e85ea5d47fd4c56464053bbebe301f1
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -106.91307794712847, "std_reward": 43.63043618024966, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-31T10:05:19.870821"}
+{"env_id": "LunarLander-v2", "mean_reward": -58.6773893623508, "std_reward": 70.13263897723591, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-31T10:09:29.632727"}