araffin
/

a2c-Pendulum-v1

Reinforcement Learning

stable-baselines3

Pendulum-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

a2c-Pendulum-v1 / results.json

araffin

Initial commit

fffa48e verified over 2 years ago

raw

history blame

159 Bytes

{"mean_reward": -141.1884953, "std_reward": 122.26897425286533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-19T22:50:12.306466"}