Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ 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: 109.20 +/- 66.94
+      value: -105.37 +/- 37.22
       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
   

logs/events.out.tfevents.1680706556.1a25f1327f79.4337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fc2007703fab5116870a1a3ba8bd144d244ed2157bc1fde59ab65a38d5fd14
+size 63169

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adfca7ee050d5965749e341a6adbf01f0a15379002b090cf1e3a8dc75e46d97d
-size 40037
+oid sha256:fac1ead6752bdf1ed700e02dc6f0cc4f5d74ab755fd8553cf18ce89290fb09ad
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 109.2, "std_reward": 66.94296079499323, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-05T14:53:59.825295"}
+{"env_id": "LunarLander-v2", "mean_reward": -105.37477053580733, "std_reward": 37.21975990399765, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-05T14:56:37.580041"}