first_commit

.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

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: ppo_lunarlander_v2
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -230.68 +/- 50.06
+      value: -202.37 +/- 53.98
       name: mean_reward
       verified: false
 ---
 
-# **ppo_lunarlander_v2** Agent playing **LunarLander-v2**
-This is a trained model of a **ppo_lunarlander_v2** agent playing **LunarLander-v2**
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ba0722e49e67381428a69b7aa548890631b14aa3152fc8b5233644e30faf9d
+oid sha256:65a1bd481efb57406a3429f5cfcab764b9fbb47b9ed7a96d6b7bf3718874bb20
 size 147389

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e18bd572ec8bedfe76caded3a3f261fdec3506943ae2ad226861dbdabeb1cf
+size 133368

results.json

@@ -1 +1 @@
-{"mean_reward": -230.6782138, "std_reward": 50.05736165329706, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-16T07:14:27.499168"}
+{"mean_reward": -202.373252, "std_reward": 53.975155331890235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-04-16T07:14:59.304252"}