Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

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: 175.80 +/- 61.32
+      value: 128.77 +/- 53.16
       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.1739289745.ac2833920c19.7052.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fe792ef38d6459ad35bb8315726fe3a7b24cd63297c6b9dd266967bc07b145
+size 306485

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253f0e4b6304f0dc7378e7ccc2960aa8eaace3a0185975f83d3c3cb9877e6234
-size 40466
+oid sha256:3549e716c64df0ebb5c78afe79f4cd5c318f2a0e5ee354264180a96880bd8b9e
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 175.8, "std_reward": 61.321774273091606, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-11T15:48:43.993991"}
+{"env_id": "LunarLander-v2", "mean_reward": 128.77097205634465, "std_reward": 53.15600613594416, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-11T16:24:52.365171"}