Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong, Mengdi Wang, Yu Bai

Keywords: partially observable reinforcement learning, POMDPs, reinforcement learning theory

TL;DR: We propose a new enhanced feedback model for learning POMDPs, and identify new broad classes of POMDPs that are sample-efficiently learnable under this feedback model.

Abstract: This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by real-world settings such as loading in game playing, we propose an enhanced feedback model called ``multiple observations in hindsight'', where after each episode of interaction with the POMDP, the learner may collect multiple additional observations emitted from the encountered latent states, but may not observe the latent states themselves. We show that sample-efficient learning under this feedback model is possible for two new subclasses of POMDPs: \emph{multi-observation revealing POMDPs} and \emph{distinguishable POMDPs}. Both subclasses generalize and substantially relax \emph{revealing POMDPs}---a widely studied subclass for which sample-efficient learning is possible under standard trajectory feedback. Notably, distinguishable POMDPs only require the emission distributions from different latent states to be \emph{different} instead of \emph{linearly independent} as required in revealing POMDPs.

Submission Number: 29