Per-decision Multi-step Temporal Difference Learning with Control Variates

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be poor, and incorporating longer sampled reward sequences into the updates. Especially in the off-policy setting, where the agent aims to learn about a policy different from the one generating its behaviour, the variance in the updates can cause learning to diverge as the number of sampled rewards used in the estimates increases. In this paper, we introduce per-decision control variates for multi-step TD algorithms, and compare them to existing methods. Our results show that including the control variates can greatly improve performance on both on and off-policy multi-step temporal difference learning tasks.

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

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

[3]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

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

[5]  Richard S. Sutton,et al.  Multi-step Off-policy Learning Without Importance Sampling Ratios , 2017, ArXiv.

[6]  Michael I. Jordan,et al.  MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING DEPARTMENT OF BRAIN AND COGNITIVE SCIENCES , 1996 .

[7]  Gavin Adrian Rummery.  Problem solving with reinforcement learning , 1995 .

[8]  Marc G. Bellemare,et al.  Safe and Efficient Off-Policy Reinforcement Learning , 2016, NIPS.

[9]  Shie Mannor,et al.  Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis , 2015, AAAI.

[10]  Mahesan Niranjan,et al.  On-line Q-learning using connectionist systems , 1994 .

[11]  Marc G. Bellemare,et al.  Q(λ) with Off-Policy Corrections , 2016, ALT.

[12]  Nan Jiang,et al.  Doubly Robust Off-policy Value Evaluation for Reinforcement Learning , 2015, ICML.

[13]  Richard S. Sutton,et al.  Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding , 1995, NIPS.

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

[15]  Philip S. Thomas,et al.  Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning , 2016, ICML.