Parallel reinforcement learning for weighted multi-criteria model with adaptive margin

@article{Hiraoka2007ParallelRL,
  title={Parallel reinforcement learning for weighted multi-criteria model with adaptive margin},
  author={Kazuyuki Hiraoka and Manabu Yoshida and Taketoshi Mishima},
  journal={Cognitive Neurodynamics},
  year={2007},
  volume={3},
  pages={17-24}
}
Reinforcement learning (RL) for a linear family of tasks is described in this paper. The key of our discussion is nonlinearity of the optimal solution even if the task family is linear; we cannot obtain the optimal policy using a naive approach. Although an algorithm exists for calculating the equivalent result to Q-learning for each task simultaneously, it presents the problem of explosion of set sizes. We therefore introduce adaptive margins to overcome this difficulty.