Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment

TL;DR

This paper introduces a novel framework combining time-varying and partial observability models for autonomous decision-making, using memory-augmented estimation and planning to improve performance in uncertain, dynamic environments.

Contribution

It proposes the TV-POMDP model and a Memory Prioritized State Estimation method, enhancing planning accuracy in time-varying, partially observable environments.

Findings

Superior performance over standard methods in simulations

Effective long-term reward optimization in dynamic environments

Validated with hardware experiments involving robots

Abstract

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system's optimal decision making strategy for mission completion. To model such environments, our work combines the previous notion of Time-Varying Markov Decision Processes (TVMDP) with partial observability and introduces Time-Varying Partially Observable Markov Decision Processes (TV-POMDP). We propose a two-pronged approach to accurately estimate and plan within the TV-POMDP: 1) Memory Prioritized State Estimation (MPSE), which leverages weighted memory to provide more accurate time-varying transition estimates; and 2) an MPSE-integrated planning strategy that optimizes long-term rewards while accounting for temporal constraint. We validate the proposed framework and algorithms using simulations and hardware, with robots exploring a partially observable, time-varying environments. Our results demonstrate superior performance over standard methods, highlighting the framework's effectiveness in stochastic, uncertain, time-varying domains.