Predicting Periodicity with Temporal Difference Learning

Temporal difference (TD) learning is an important approach in reinforcement learning, as it combines ideas from dynamic programming and Monte Carlo methods in a way that allows for online and incremental model-free learning. A key idea of TD learning is that it is learning predictive knowledge about the environment in the form of value functions, from which it can derive its behavior to address long-term sequential decision making problems. The agent's horizon of interest, that is, how immediate or long-term a TD learning agent predicts into the future, is adjusted through a discount rate parameter. In this paper, we introduce an alternative view on the discount rate, with insight from digital signal processing, to include complex-valued discounting. Our results show that setting the discount rate to appropriately chosen complex numbers allows for online and incremental estimation of the Discrete Fourier Transform (DFT) of a signal of interest with TD learning. We thereby extend the types of knowledge representable by value functions, which we show are particularly useful for identifying periodic effects in the reward sequence.

[1]  Patrick M. Pilarski,et al.  Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction , 2011, AAMAS.

[2]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[3]  Tom Schaul,et al.  Reinforcement Learning with Unsupervised Auxiliary Tasks , 2016, ICLR.

[4]  Marc G. Bellemare,et al.  A Distributional Perspective on Reinforcement Learning , 2017, ICML.

[5]  Richard S. Sutton,et al.  Generalization in ReinforcementLearning : Successful Examples UsingSparse Coarse , 1996 .

[6]  Marc G. Bellemare,et al.  Distributional Reinforcement Learning with Quantile Regression , 2017, AAAI.

[7]  Doina Precup,et al.  Eligibility Traces for Off-Policy Policy Evaluation , 2000, ICML.

[8]  Shimon Whiteson,et al.  A theoretical and empirical analysis of Expected Sarsa , 2009, 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning.

[9]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[10]  George Konidaris,et al.  Value Function Approximation in Reinforcement Learning Using the Fourier Basis , 2011, AAAI.

[11]  Jeffrey S. Rosenthal,et al.  Convergence Rates for Markov Chains , 1995, SIAM Rev..

[12]  Richard S. Sutton,et al.  Multi-timescale nexting in a reinforcement learning robot , 2011, Adapt. Behav..

[13]  Richard S. Sutton,et al.  TD Models: Modeling the World at a Mixture of Time Scales , 1995, ICML.