sb3
/

ars-Pendulum-v1

Reinforcement Learning

stable-baselines3

Pendulum-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ars-Pendulum-v1 / results.json

araffin

Initial commit

24dde1d over 2 years ago

raw

history blame

158 Bytes

{"mean_reward": -282.0764697, "std_reward": 194.5136277118124, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T19:24:54.936080"}