Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -105.86 +/- 93.13
+      value: -88.04 +/- 80.81
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677610442.f57ae78282d8.5524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1baac4b4bdfbd0f2812ec29534d96d9fdbbbcade60500653bb4f55a110158fa5
+size 1253247

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0db48b7e3e0066f01f6a39afbc873180521e7ab5359920e2409f8169f011ee86
+oid sha256:ab15a16b18b87bf962ef37e699d27733152d033658070d279c74e1eede715b34
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -105.85958754966116, "std_reward": 93.13000802963951, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T18:52:22.604753"}
+{"env_id": "LunarLander-v2", "mean_reward": -88.0401924565763, "std_reward": 80.80516244205911, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-28T19:23:29.137402"}