The Predictron: End-To-End Learning and PlanningDownload PDF

01 Dec 2024 (modified: 21 Jul 2022)Submitted to ICLR 2017Readers: Everyone
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, thereby focusing the model upon the aspects of the environment most relevant to planning. 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.
Conflicts: google.com
Keywords: Deep learning, Reinforcement Learning, Supervised Learning, Semi-Supervised Learning
21 Replies

Loading