The Predictron: End-To-End Learning and Planning
Abstract
One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple "imagined" planning steps. Each forward pass of the predictron accumulates internal rewards and values over multiple planning depths. The predictron is trained end-to-end so as to make these accumulated values accurately approximate the true value function. We applied the predictron to procedurally generated random mazes and a simulator for the game of pool. The predictron yielded significantly more accurate predictions than conventional deep neural network architectures.
Cite
@article{arxiv.1612.08810,
title = {The Predictron: End-To-End Learning and Planning},
author = {David Silver and Hado van Hasselt and Matteo Hessel and Tom Schaul and Arthur Guez and Tim Harley and Gabriel Dulac-Arnold and David Reichert and Neil Rabinowitz and Andre Barreto and Thomas Degris},
journal= {arXiv preprint arXiv:1612.08810},
year = {2017}
}
Comments
Camera-ready version, ICML 2017, with supplement