Thinking Fast and Slow with Deep Learning and Tree Search

Sequential decision making problems, such as structured prediction, robotic control, and game playing, require a combination of planning policies and generalisation of those plans. In this paper, we present Expert Iteration (ExIt), a novel reinforcement learning algorithm which decomposes the problem into separate planning and generalisation tasks. Planning new policies is performed by tree search, while a deep neural network generalises those plans. Subsequently, tree search is improved by using the neural network policy to guide search, increasing the strength of new plans. In contrast, standard deep Reinforcement Learning algorithms rely on a neural network not only to generalise plans, but to discover them too. We show that ExIt outperforms REINFORCE for training a neural network to play the board game Hex, and our final tree search agent, trained tabula rasa, defeats MoHex 1.0, the most recent Olympiad Champion player to be publicly released.

[1]  Jonathan Evans.  Heuristic and analytic processes in reasoning , 1984 .

[2]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[3]  D. Kahneman.  Maps of Bounded Rationality: Psychology for Behavioral Economics , 2003 .

[4]  Michael R. Genesereth,et al.  General Game Playing: Overview of the AAAI Competition , 2005, AI Mag..

[5]  Csaba Szepesvári,et al.  Bandit Based Monte-Carlo Planning , 2006, ECML.

[6]  David Silver,et al.  Combining online and offline knowledge in UCT , 2007, ICML '07.

[7]  John Langford,et al.  Search-based structured prediction , 2009, Machine Learning.

[8]  Ryan B. Hayward,et al.  Monte Carlo Tree Search in Hex , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[9]  Geoffrey J. Gordon,et al.  A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning , 2010, AISTATS.

[10]  Shih-Chieh Huang,et al.  MoHex 2.0: A Pattern-Based MCTS Hex Player , 2013, Computers and Games.

[11]  Joakim Nivre,et al.  Training Deterministic Parsers with Non-Deterministic Oracles , 2013, TACL.

[12]  Honglak Lee,et al.  Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning , 2014, NIPS.

[13]  J. Andrew Bagnell,et al.  Reinforcement and Imitation Learning via Interactive No-Regret Learning , 2014, ArXiv.

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[16]  John Langford,et al.  Learning to Search Better than Your Teacher , 2015, ICML.

[17]  Kenny Young,et al.  Neurohex: A Deep Q-learning Hex Agent , 2016, CGW@IJCAI.

[18]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[19]  Venu Govindaraju,et al.  Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks , 2016, ICML.

[20]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[21]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[22]  Shimon Whiteson,et al.  TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning , 2017, ICLR 2018.