Deep Exploration via Bootstrapped DQN

Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of randomized value functions. Unlike dithering strategies such as epsilon-greedy exploration, bootstrapped DQN carries out temporally-extended (or deep) exploration; this can lead to exponentially faster learning. We demonstrate these benefits in complex stochastic MDPs and in the large-scale Arcade Learning Environment. Bootstrapped DQN substantially improves learning times and performance across most Atari games.

[1]  W. R. Thompson.  ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES , 1933 .

[2]  D. Freedman,et al.  Some Asymptotic Theory for the Bootstrap , 1981 .

[3]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[4]  Raul Cano.  On The Bayesian Bootstrap , 1992 .

[5]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[6]  Gerald Tesauro,et al.  Temporal Difference Learning and TD-Gammon , 1995, J. Int. Comput. Games Assoc..

[7]  Apostolos Burnetas,et al.  Optimal Adaptive Policies for Markov Decision Processes , 1997, Math. Oper. Res..

[8]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[9]  Malcolm J. A. Strens,et al.  A Bayesian Framework for Reinforcement Learning , 2000, ICML.

[10]  Ronen I. Brafman,et al.  R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning , 2001, J. Mach. Learn. Res..

[11]  Sham M. Kakade,et al.  On the sample complexity of reinforcement learning. , 2003 .

[12]  Michael Kearns,et al.  Near-Optimal Reinforcement Learning in Polynomial Time , 2002, Machine Learning.

[13]  Michael L. Littman,et al.  A theoretical analysis of Model-Based Interval Estimation , 2005, ICML.

[14]  Tao Wang,et al.  Bayesian sparse sampling for on-line reward optimization , 2005, ICML.

[15]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[16]  M. Kenward,et al.  An Introduction to the Bootstrap , 2007 .

[17]  Peter Auer,et al.  Near-optimal Regret Bounds for Reinforcement Learning , 2008, J. Mach. Learn. Res..

[18]  Alex Graves,et al.  Practical Variational Inference for Neural Networks , 2011, NIPS.

[19]  Purnamrita Sarkar,et al.  A scalable bootstrap for massive data , 2011, 1112.5016.

[20]  Peter Dayan,et al.  Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search , 2012, NIPS.

[21]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[22]  A. Owen,et al.  Bootstrapping data arrays of arbitrary order , 2011, 1106.2125.

[23]  Zheng Wen,et al.  Efficient Exploration and Value Function Generalization in Deterministic Systems , 2013, NIPS.

[24]  Ian.  ( More ) Efficient Reinforcement Learning via Posterior Sampling , 2013 .

[25]  Benjamin Van Roy,et al.  (More) Efficient Reinforcement Learning via Posterior Sampling , 2013, NIPS.

[26]  Benjamin Van Roy,et al.  Near-optimal Reinforcement Learning in Factored MDPs , 2014, NIPS.

[27]  Peter Dayan,et al.  Bayes-Adaptive Simulation-based Search with Value Function Approximation , 2014, NIPS.

[28]  Benjamin Van Roy,et al.  Learning to Optimize via Posterior Sampling , 2013, Math. Oper. Res..

[29]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[30]  Rémi Munos,et al.  From Bandits to Monte-Carlo Tree Search: The Optimistic Principle Applied to Optimization and Planning , 2014, Found. Trends Mach. Learn..

[31]  Benjamin Van Roy,et al.  Model-based Reinforcement Learning and the Eluder Dimension , 2014, NIPS.

[32]  Sergey Levine,et al.  Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models , 2015, ArXiv.

[33]  Shie Mannor,et al.  Thompson Sampling for Learning Parameterized Markov Decision Processes , 2014, COLT.

[34]  Csaba Szepesvári,et al.  Bayesian Optimal Control of Smoothly Parameterized Systems , 2015, UAI.

[35]  Julien Cornebise,et al.  Weight Uncertainty in Neural Network , 2015, ICML.

[36]  Ryan P. Adams,et al.  Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks , 2015, ICML.

[37]  Benjamin Van Roy,et al.  Bootstrapped Thompson Sampling and Deep Exploration , 2015, ArXiv.

[38]  Shane Legg,et al.  Massively Parallel Methods for Deep Reinforcement Learning , 2015, ArXiv.

[39]  Julien Cornebise,et al.  Weight Uncertainty in Neural Networks , 2015, ArXiv.

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

[41]  Ariel D. Procaccia,et al.  Variational Dropout and the Local Reparameterization Trick , 2015, NIPS.

[42]  Christoph Dann,et al.  Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning , 2015, NIPS.

[43]  Marc G. Bellemare,et al.  The Arcade Learning Environment: An Evaluation Platform for General Agents , 2012, J. Artif. Intell. Res..

[44]  Benjamin Van Roy,et al.  Generalization and Exploration via Randomized Value Functions , 2014, ICML.

[45]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[46]  Tom Schaul,et al.  Dueling Network Architectures for Deep Reinforcement Learning , 2015, ICML.

[47]  Sergey Levine,et al.  End-to-End Training of Deep Visuomotor Policies , 2015, J. Mach. Learn. Res..

[48]  Tom Schaul,et al.  Prioritized Experience Replay , 2015, ICLR.

[49]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[50]  Yee Whye Teh,et al.  Distributed Bayesian Learning with Stochastic Natural Gradient Expectation Propagation and the Posterior Server , 2015, J. Mach. Learn. Res..

[51]  T. L. Lai Andherbertrobbins.  Asymptotically Efficient Adaptive Allocation Rules , 2022 .