Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- LunarLander-v3
+- CartPole-v1
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,26 +13,26 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v3
-      type: LunarLander-v3
+      name: CartPole-v1
+      type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: -172.97 +/- 102.64
+      value: 186.40 +/- 49.43
       name: mean_reward
       verified: false
 ---
 
-    # PPO Agent Playing LunarLander-v3
+    # PPO Agent Playing CartPole-v1
 
-    This is a trained model of a PPO agent playing LunarLander-v3.
+    This is a trained model of a PPO agent playing CartPole-v1.
 
     # Hyperparameters
     ```python
     {'exp_name': 'unit8_part1',
-'gym_id': 'LunarLander-v3',
+'gym_id': 'CartPole-v1',
 'learning_rate': 0.00025,
 'seed': 1,
-'total_timesteps': 50000,
+'total_timesteps': 100000,
 'torch_deterministic': True,
 'cuda': True,
 'track': False,

logs/events.out.tfevents.1741910742.KASHYYYK.33927.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d864048111e6a4743368259264312e13cd3d1b0345d4bdd53e56b32b89bef349
+size 175856

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f90a4c3d507d195b23d9f93997d0dd3bc3b193bd7153d577853aa3d4d1c84f2
-size 43026
+oid sha256:8acd7f42cf3a72632a672b5be4ae2dadbd67c6383e3c10f29e15eef8ad6da7f7
+size 40466

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -172.96513640485938, "std_reward": 102.63833553579478, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T01:04:48.782567"}
+{"env_id": "CartPole-v1", "mean_reward": 186.4, "std_reward": 49.43116425899758, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T01:06:33.467339"}