Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.11 +/- 85.84
+      value: -9.71 +/- 89.95
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 100000
 'learning_rate': 0.0002
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1710913020.78f44feafe37.35786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e8f0739c5946e68ae7a32dd76983f782ec24a5fde615a5069f7b831be3e58a
+size 81801

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062c911346ef5df8da67d8c9693d9b31677062868f7f5b1c10a42b1b6ef61a35
+oid sha256:f252e6607b1e7044824be927174094e35ae5a230fdfb8e58de86b89f85b15e6e
 size 111402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.109185869574, "std_reward": 85.83953411127959, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-20T05:36:35.101908"}
+{"env_id": "LunarLander-v2", "mean_reward": -9.713312897685213, "std_reward": 89.94896240166061, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-20T05:40:33.252303"}