Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -197.90 +/- 134.71
+      value: 132.00 +/- 14.30
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1688097270.63d6cc87c71b.2797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6736b994e6b32434ff9c69689b49e7bdbc8641c483ba8ab52ff287894063a9db
+size 337868

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e541b1708d23f31c9369b677df43ff11571f22fa1554ebef621b3cc7dae1051e
+oid sha256:6df86de940e32a6f3ed5275f1165f8247c56be91f034726aa62f20bf2aa9dcda
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -197.90092346524793, "std_reward": 134.71187451612633, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-30T03:53:48.645477"}
+{"env_id": "LunarLander-v2", "mean_reward": 131.99939510886597, "std_reward": 14.295565567512108, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-30T04:15:39.876986"}