Upload PPO LunarLander-v2 trained baseline agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 270.27 +/- 20.40
+      value: 265.63 +/- 17.94
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -22,6 +22,7 @@ model-index:
 
 
 
+
 # **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).

ppo2-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5386cdbe56c71b1561bb72e563b242ee2a4c70c85ba528f2daef6e6b619dc4c
+oid sha256:1e52224c009a7f44104c86637d0691cae6b7ae1ffa4616037ab7b19ba8201558
 size 142955

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49aac4e3bb03b41f15f5e897dd4eb015f0ce909a2c33ce0c58b5a6ae43d61a94
-size 249453
+oid sha256:4c7397e7384f313b7faf450f5351ff81d32deda5f0f974051b8fec8f219db07e
+size 213517

results.json

@@ -1 +1 @@
-{"mean_reward": 270.2667875228859, "std_reward": 20.39528307968006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T21:09:43.693026"}
+{"mean_reward": 265.63357266940875, "std_reward": 17.94413586357526, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-28T21:14:07.570970"}