HumanCompatibleAI
/

ppo-Pendulum-v1

Reinforcement Learning

stable-baselines3

Pendulum-v1

deep-reinforcement-learning

Eval Results

Model card Files Files and versions Community

ppo-Pendulum-v1 / results.json

ernestum

Initial commit

404c2d1 over 2 years ago

raw

history blame

165 Bytes

{"mean_reward": -336.60077279999996, "std_reward": 406.5254085374081, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T16:30:45.639168"}