你即將離開本站

並前往https://medium.com/@mikeshi/the-unsatisfactory-answer-is-that-its-arbitrary-cartpole-v0-has-a-termination-condition-of-200-909da2167e38

The unsatisfactory answer is that it's arbitrary, CartPole v0 has ...

The unsatisfactory answer is that it's arbitrary, CartPole v0 has a termination condition of 200 timesteps, and v1 was chosen to have 500.

確定！ 回上一頁

查詢 「CartPole v0 vs v1」的人也找了：

  1. CartPole
    2.
  2. CartPole DQN
    3.
  3. OpenAI Gym
    4.
  4. Gym environment
    5.
  5. Env step
    6.
  6. Pip install gym
    7.
  7. Gym reward threshold
    8.
  8. Acrobot
    9.