Sparse tree search optimality guarantees in POMDPs with continuous observation spaces

by   Michael H. Lim, et al.

Partially observable Markov decision processes (POMDPs) with continuous state and observation spaces have powerful flexibility for representing real-world decision and control problems, but are notoriously difficult to solve. Recent online sampling-based algorithms that use observation likelihood weighting have shown unprecedented effectiveness in domains with continuous observation spaces. However there has been no formal theoretical justification for this technique. This work offers such a justification, proving that a simplified algorithm, partially observable weighted sparse sampling (POWSS), will estimate Q-values accurately with high probability and can be made to perform arbitrarily near the optimal solution by increasing computational power.


page 1

page 2

page 3

page 4


Voronoi Progressive Widening: Efficient Online Solvers for Continuous Space MDPs and POMDPs with Provably Optimal Components

Markov decision processes (MDPs) and partially observable MDPs (POMDPs) ...

Information-Guided Robotic Maximum Seek-and-Sample in Partially Observable Continuous Environments

We present PLUMES, a planner to localizing and collecting samples at the...

POMCPOW: An online algorithm for POMDPs with continuous state, action, and observation spaces

Online solvers for partially observable Markov decision processes have b...

A Minimax Learning Approach to Off-Policy Evaluation in Partially Observable Markov Decision Processes

We consider off-policy evaluation (OPE) in Partially Observable Markov D...

Scalable Accelerated Decentralized Multi-Robot Policy Search in Continuous Observation Spaces

This paper presents the first ever approach for solving continuous-obser...

A Scalable Method for Solving High-Dimensional Continuous POMDPs Using Local Approximation

Partially-Observable Markov Decision Processes (POMDPs) are typically so...

Improved POMDP Tree Search Planning with Prioritized Action Branching

Online solvers for partially observable Markov decision processes have d...