AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes

Marc Rigter, Bruno Lacerda, Nick Hawes

AAAI 2021 · Bandits and online learning › RL theory and MDPs · approach: Average-reward and latent MDPs · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the regret Bellman recursion rather than myopic CEMRMinimax regret planning · Disaster rescue, medical decision making, and underwater glidermaximum regretImproved
Use larger n-step options to retain uncertainty dependence over longer action sequences (ablation)reg · Disaster rescue, medical decision making, and underwater glidermaximum regretImproved
Use stochastic rather than deterministic option policies (ablation)reg · Disaster rescue and underwater glidermaximum regretImproved
Use stochastic rather than deterministic option policies (ablation)reg · Disaster rescue and underwater glidercomputation timeHurt
Extend CEMR to use n-step options (ablation)CEMR · Dependent-uncertainty domainsmaximum regretImproved
Use action pruning (ablation)reg, CEMR, and MILP · Evaluation domainscomputation timeImproved
Use action pruning (ablation)reg, CEMR, and MILP · Evaluation domainsperformanceNo clear effect
Use minimax regret with n-step options rather than the strongest reported baselinereg · Disaster rescue and medical decision makingmaximum regret on the larger test setImproved
Use minimax regret with larger n-step optionsreg · Underwater glidermaximum regret on the larger test setImproved
Use the proposed approach rather than MILPMinimax regret planning · Medical decision makingsolution availability within the time limit: 600sImproved
Use larger n-step options rather than MILPreg · Dependent-uncertainty domainsmaximum regretImproved
Claim exact minimax regret for independent uncertainty sets using the n=1 adversary formulationProposed algorithm · Independent uncertainty setsexactnessHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy