ppo_lunar_11_32Envs_BigBuffer

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 281.27 +/- 18.42
+      value: 287.76 +/- 17.66
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -32,6 +32,7 @@ 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).
   

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ffc6f4fa7c58d6cd0594e17bfa527b8917c0a3feaaaa0408b5cce9ff95e508
+oid sha256:c214bf1cf0419bc4bb1bd844626303d270bebd2955bc56286726a83cf22beb66
 size 144495

results.json

@@ -1 +1 @@
-{"mean_reward": 281.26577678377987, "std_reward": 18.421893919125388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T13:28:45.887983"}
+{"mean_reward": 287.7636687513371, "std_reward": 17.655138427963188, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T13:31:02.197312"}