AI plays Trackmania - Map5

Поделиться
HTML-код
  • Опубликовано: 21 ноя 2024

Комментарии • 11

  • @Shweetz
    @Shweetz Год назад +3

    For future reference, in this video the AI was not yet allowed to accelerate and brake at the same time, yet got a very decent time!

  • @spacecowboy511
    @spacecowboy511 Год назад +4

    These self driving cars are getting out of hand

  • @JFx09
    @JFx09 4 месяца назад

    can you make a tutorial

  • @kayuzz323
    @kayuzz323 Год назад +1

    why is it wiggling on straights, does that actually help?

    • @linesight-rl
      @linesight-rl  Год назад +1

      The agent tries to predict the remaining racing time if it executes action A, B or C.
      The impact of wiggling on overall racing time is probably so small that the agent is unable to differentiate the actions, as long as they accelerate.
      There is no reward for the agent to press as few buttons as possible, or for it to keep the same action several frames in a row.

    • @howuhh8960
      @howuhh8960 Год назад

      @@linesight-rl this also can be caused by stochastic policy, on evaluation it's better to disable all randomness

    • @howuhh8960
      @howuhh8960 Год назад

      @@linesight-rl cool project anyway!

    • @linesight-rl
      @linesight-rl  Год назад +1

      @@howuhh8960 In this case, there is no stochastic policy. The reinforcement learning algorithm is value-based.

    • @howuhh8960
      @howuhh8960 Год назад

      @@linesight-rl very cool, keep going!

  • @CaptainXJ
    @CaptainXJ 4 месяца назад

    alas, still no "pin of shame" How will people know that AI is Yahweh?