Pith. sign in

REVIEW 1 cited by

Under-Approximating Expected Total Rewards in POMDPs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.08772 v1 pith:KK2GQMBS submitted 2022-01-21 cs.AI cs.LO

Under-Approximating Expected Total Rewards in POMDPs

classification cs.AI cs.LO
keywords expectedtotalpomdpbelieffindminimalproblemreward
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We consider the problem: is the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) below a given threshold? We tackle this -- generally undecidable -- problem by computing under-approximations on these total expected rewards. This is done by abstracting finite unfoldings of the infinite belief MDP of the POMDP. The key issue is to find a suitable under-approximation of the value function. We provide two techniques: a simple (cut-off) technique that uses a good policy on the POMDP, and a more advanced technique (belief clipping) that uses minimal shifts of probabilities between beliefs. We use mixed-integer linear programming (MILP) to find such minimal probability shifts and experimentally show that our techniques scale quite well while providing tight lower bounds on the expected total reward.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Scaling Observation-aware Planning in Uncertain Domains

    cs.AI 2026-05 unverdicted novelty 6.0

    A POMDP decomposition method scales solving of the Sensor Selection Problem and Positional Observability Problem by 3 and 5 orders of magnitude in instance size and runtime.