Off-Policy Evaluation for Action-Dependent Non-Stationary Environments

by   Yash Chandak, et al.

Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such methods because real-world problems are often subject to changes due to external factors (passive non-stationarity), changes induced by interactions with the system itself (active non-stationarity), or both (hybrid non-stationarity). In this work, we take the first steps towards the fundamental challenge of on-policy and off-policy evaluation amidst structured changes due to active, passive, or hybrid non-stationarity. Towards this goal, we make a higher-order stationarity assumption such that non-stationarity results in changes over time, but the way changes happen is fixed. We propose, OPEN, an algorithm that uses a double application of counterfactual reasoning and a novel importance-weighted instrument-variable regression to obtain both a lower bias and a lower variance estimate of the structure in the changes of a policy's past performances. Finally, we show promising results on how OPEN can be used to predict future performances for several domains inspired by real-world applications that exhibit non-stationarity.


page 1

page 2

page 3

page 4


Optimizing for the Future in Non-Stationary MDPs

Most reinforcement learning methods are based upon the key assumption th...

Towards Safe Policy Improvement for Non-Stationary MDPs

Many real-world sequential decision-making problems involve critical sys...

Decision Making in Non-Stationary Environments with Policy-Augmented Monte Carlo Tree Search

Decision-making under uncertainty (DMU) is present in many important pro...

Universal Off-Policy Evaluation

When faced with sequential decision-making problems, it is often useful ...

Lifelong Learning with a Changing Action Set

In many real-world sequential decision making problems, the number of av...

A breakpoint detection in the mean model with heterogeneous variance on fixed time-intervals

This work is motivated by an application for the homogeneization of GNSS...

Please sign up or login with your details

Forgot password? Click here to reset