Learning Approximate Stochastic Transition Models [article]

Yuhang Song, Christopher Grimm, Xianming Wang, Michael L. Littman
2017 arXiv   pre-print
We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently popular generative adversarial networks struggle to learn these stochastic transition models but a modification to their loss functions results in a powerful learning algorithm for this class of problems.
arXiv:1710.09718v1 fatcat:da6rr6m7mrgg3bin343tzj3pru