Q($\lambda$) with Off-Policy Corrections

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of transition probabilities. We prove that such approximate corrections are sufficient for off-policy convergence both in policy evaluation and control, provided certain conditions. These conditions relate the distance between the target and behavior policies, the eligibility trace parameter and the discount factor, and formalize an underlying tradeoff in off-policy TD($\lambda$). We illustrate this theoretical relationship empirically on a continuous-state control task.

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

[2]  Richard S. Sutton,et al.  Off-policy learning based on weighted importance sampling with linear computational complexity , 2015, UAI.

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

[4]  H. Kahn,et al.  Methods of Reducing Sample Size in Monte Carlo Computations , 1953, Oper. Res..

[5]  Richard S. Sutton,et al.  True online TD(λ) , 2014, ICML 2014.

[6]  Preben Alstrøm,et al.  Learning to Drive a Bicycle Using Reinforcement Learning and Shaping , 1998, ICML.

[7]  Peter Dayan,et al.  Analytical Mean Squared Error Curves for Temporal Difference Learning , 1996, Machine Learning.

[8]  Michael Kearns,et al.  Bias-Variance Error Bounds for Temporal Difference Updates , 2000, COLT.

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

[10]  R. Bellman.  Dynamic programming. , 1957, Science.

[11]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

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

[13]  Tommi S. Jaakkola,et al.  Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms , 2000, Machine Learning.

[14]  Martha White,et al.  Emphatic Temporal-Difference Learning , 2015, ArXiv.

[15]  Jing Peng,et al.  Incremental multi-step Q-learning , 1994, Machine Learning.

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

[17]  Hado Philip van Hasselt,et al.  Insights in reinforcement rearning : formal analysis and empirical evaluation of temporal-difference learning algorithms , 2011 .