HumanCompatibleAI
/

ppo-seals-HalfCheetah-v1

Reinforcement Learning

stable-baselines3

seals/HalfCheetah-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ppo-seals-HalfCheetah-v1 / results.json

ernestum

Initial commit

bc20a15 9 months ago

raw history blame contribute delete

No virus

158 Bytes

{"mean_reward": 1675.7591266, "std_reward": 45.89236738692049, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-19T11:58:11.147177"}