THE CONFERENCE
FOR AUTHORS
FOR PARTICIPANTS

 
Talk
The Predictron: End-To-End Learning and Planning
David Silver · Hado van Hasselt · Matteo Hessel · Tom Schaul · Arthur Guez · Tim Harley · Gabriel Dulac-Arnold · David Reichert · Neil Rabinowitz · Andre Barreto · Thomas Degris

Wed Aug 9th 02:24 -- 02:42 PM @ C4.5
in Deep reinforcement learning 1 »

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.

Author Information

David Silver (Google DeepMind)
Hado van Hasselt (DeepMind)
Matteo Hessel (Deep Mind)
Tom Schaul (DeepMind)
Arthur Guez (Google DeepMind)
Tim Harley (DeepMind)
Gabriel Dulac-Arnold (Google DeepMind)
David Reichert (DeepMind)
Neil Rabinowitz (DeepMind)
Andre Barreto (Google DeepMind)
Thomas Degris (DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors