Croolch
/

ppo-LunarLander-v2

Reinforcement Learning

stable-baselines3

TensorBoard

LunarLander-v2

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Metrics Training metrics Community

ppo-LunarLander-v2 / results.json

Croolch

0624 ppo 1,000,000 steps

e4f1520 verified 6 months ago

raw

history blame

157 Bytes

{"mean_reward": 226.2310303, "std_reward": 77.63136796588182, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-24T14:07:08.328209"}