Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -123.95 +/- 82.55
+      value: -56.86 +/- 40.97
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1679059562.fa3c293dcd0c.11734.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937a12f92c3d14c42001d1c29a1546eb1204fbcd316b0e9ffc64f6e6286b5584
+size 1265022

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:ebb378896b2cb4c43e971f50d7380e681cb99523b73cd341f85c99706c03d9df
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -123.95494678984218, "std_reward": 82.54573190409751, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-17T13:24:42.008415"}
+{"env_id": "LunarLander-v2", "mean_reward": -56.86444069537002, "std_reward": 40.97023956372647, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-17T13:52:36.832186"}