Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -134.05 +/- 75.55
+      value: -106.91 +/- 43.63
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ 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.1667210651.35d33fc0db11.626.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b19654cb9e0203a203b9c9135fc892a40659dfa98c6b951e82e6b6bd1fdd3a7
+size 100844

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6423a7cec329cbd63e1e7c57e08876cf3d53b8f98a6852ac067ecea725e9c4a9
+oid sha256:213bac8bad39cb373c9f15f510ce983e1d668432ce741b493d008f8508a1b89f
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -134.04889500181562, "std_reward": 75.55306984126035, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-31T10:03:30.077900"}
+{"env_id": "LunarLander-v2", "mean_reward": -106.91307794712847, "std_reward": 43.63043618024966, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-31T10:05:19.870821"}