A minimax learning approach to off-policy evaluation in confounded Partially Observable Markov Decision Processes

Shi, Chengchun, Uehara, Masatoshi, Uehara, Masatoshi, Huang, Jiawei and Jiang, Nan (2022) A minimax learning approach to off-policy evaluation in confounded Partially Observable Markov Decision Processes. In: Proceedings of the 39th International Conference on Machine Learning. International Conference on Machine Learning. (In Press)

Text (RL_POMDP_OPE) - Accepted Version Pending embargo until 1 January 2100. Download (928kB) | Request a copy

• Author
• Publisher

Abstract

We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent variables. Existing works either assume no unmeasured confounders, or focus on settings where both the observation and the state spaces are tabular. In this work, we first propose novel identification methods for OPE in POMDPs with latent confounders, by introducing bridge functions that link the target policy’s value and the observed data distribution. We next propose minimax estimation methods for learning these bridge functions, and construct three estimators based on these estimated bridge functions, corresponding to a value function-based estimator, a marginalized importance sampling estimator, and a doubly-robust estimator. Our proposal permits general function approximation and is thus applicable to settings with continuous or large observation/state spaces. The nonasymptotic and asymptotic properties of the proposed estimators are investigated in detail.

Item Type:	Book Section
Divisions:	Statistics
Date Deposited:	16 May 2022 10:42
Last Modified:	15 Sep 2023 10:17
URI:	http://eprints.lse.ac.uk/id/eprint/115104

Actions (login required)

View Item