Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -185.16 +/- 106.08
+      value: -38.53 +/- 88.82
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1703595104.cybertron.1103.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1298e2ca67ee1bdc05b89fde80ab1752e131e2ac972ab295449708f4d04f5eb
+size 670881

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff47c2e0f04dc7c3c3d0ba4c9024580254d54c878e5b18df450e87a58b7da10
-size 43026
+oid sha256:90ec1bb294ab91145c06f690741e789ab992b53a8bb13a508045025421968427
+size 672534

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -185.15573434038396, "std_reward": 106.07907470715, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T20:47:07.588705"}
+{"env_id": "LunarLander-v2", "mean_reward": -38.52591058773196, "std_reward": 88.81729419429954, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:00:28.970749"}