Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,26 +13,26 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 39.40 +/- 13.15
+      value: -103.57 +/- 53.40
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
     
   # Hyperparameters
   ```python
-  {'exp_name': 'LunarLander-v2'
-'gym_id': 'CartPole-v1'
+  {'exp_name': 'ppo'
+'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 2500
+'total_timesteps': 100000
 'torch_determistic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1696754069.56f7c4cf2aad.32694.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d852abe8f7e1bd737b35e0f7d46b6d4988a365a6d2d02861338f77ccef204a87
+size 50988

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0085543976bb8cd74201ccc131210af00ee8b34eac49fac99afe77a111b90fd
-size 40037
+oid sha256:46f5b662e04fb0b2df8d54c047377a9b851f33c5b9a4f7fbe597e921f9e56e5a
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 39.4, "std_reward": 13.154466921924278, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-08T08:33:45.513259"}
+{"env_id": "LunarLander-v2", "mean_reward": -103.57263886083982, "std_reward": 53.40109522533377, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-08T08:34:56.648167"}