Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 30.50 +/- 14.87
+      value: 53.90 +/- 25.03
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'CartPole-v1'
-'total_timesteps': 500000
+'total_timesteps': 2000000
 'learning_rate': 0.0001
 'num_envs': 64
 'num_steps': 512

logs/events.out.tfevents.1761058618.auriga.705629.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c394169495b7e361f9f98e91a7595cf0f7dc9106bcb0e0001618b673f79a3c
+size 3091867

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8fbb095d5792896ef77fe22b8441c20d5caedbdaa0ac4c2e02f462edbd448db
+oid sha256:59cef786bb6182b26a248aeabb846bdc37cc477f1b88d0de6b3ec10097306f9b
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 30.5, "std_reward": 14.867750334196495, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-21T16:56:30.408693"}
+{"env_id": "CartPole-v1", "mean_reward": 53.9, "std_reward": 25.025786700921113, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-21T16:58:49.452102"}