qgallouedec
/

trpo-HalfCheetah-v3-996877779

Reinforcement Learning

stable-baselines3

HalfCheetah-v3

deep-reinforcement-learning

HalfCheetah-v4

Eval Results

Model card Files Files and versions Community

trpo-HalfCheetah-v3-996877779 / results.json

Quentin Gallouédec

Initial commit

62f1634 over 1 year ago

raw history blame contribute delete

No virus

159 Bytes

{"mean_reward": 6347.4905271, "std_reward": 124.64465828255614, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T16:18:06.368731"}