sb3
/

ddpg-Pendulum-v1

Reinforcement Learning

stable-baselines3

Pendulum-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ddpg-Pendulum-v1 / results.json

araffin

Initial commit

34fd2f5 over 2 years ago

raw

history blame

159 Bytes

{"mean_reward": -211.6450113, "std_reward": 134.04952401875647, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-02T22:22:19.359143"}