Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -138.92 +/- 95.60
+      value: 105.57 +/- 71.90
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677766794.f44a95294c95.13315.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d4c44d1567024ccc928f7cf04e412ca89a470bcbff07d8ab2039ef56665113
+size 659828

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -138.91661212253376, "std_reward": 95.6021109953973, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T14:18:52.900584"}
+{"env_id": "LunarLander-v2", "mean_reward": 105.56818861381184, "std_reward": 71.89722611065918, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T14:34:22.109538"}