HumanCompatibleAI
/

sac-seals-Ant-v1

Reinforcement Learning

stable-baselines3

seals/Ant-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

sac-seals-Ant-v1 / results.json

ernestum

Initial commit

4e2f322 about 1 year ago

raw

history blame

165 Bytes

{"mean_reward": 1004.1500469999999, "std_reward": 26.598463652396816, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:54:05.812092"}