HumanCompatibleAI
/

sac-seals-Walker2d-v0

Reinforcement Learning

stable-baselines3

seals/Walker2d-v0

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

sac-seals-Walker2d-v0 / results.json

ernestum

Initial commit

8f03e69 over 2 years ago

raw

history blame

159 Bytes

{"mean_reward": 5483.5284099, "std_reward": 1474.7914335759533, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-27T17:07:09.427002"}