Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -1.61 +/- 78.53
+      value: -200.77 +/- 140.43
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1710495671.794eb3b1a1ff.19696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22401bdb2f742bd611176a74d73a4a83fc485652dc1f522e37154a6f7c8344bf
+size 109723

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccce4430cd2484cb7e2271f5e70f49147c1e0fa609462c182399fdfbd028f05
+oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -1.6145747349453203, "std_reward": 78.5276328746948, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-15T09:39:14.326499"}
+{"env_id": "LunarLander-v2", "mean_reward": -200.7701701355416, "std_reward": 140.43332718180693, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-15T09:41:54.935246"}