RLAI Reinforcement Learning and Artificial Intelligence (RLAI)

a simple plan (for achieving AI)

  1. goals and affect are by reward and value

  2. immediate decision making is by actor-critic style RL

  3. planning is by repeated projection and sampling

  4. knowledge is experiential

  5. abstraction is by compositional, option-style predictions

  6. function approximation is linear

Extend this Page   How to edit   Style   Subscribe   Notify   Suggest   Help   This open web page hosted at the University of Alberta.