AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs

Marek Petrik, Reazul Hasan Russel

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Distributionally robust optimization · 26 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 RSVF instead of BCI to construct value-adapted ambiguity setsBayesian robust MDP safe return estimation · Single-state Bellman update, uniform Dirichlet priorexpected regretImproved
Use RSVF instead of Hoeffding ambiguity setsrobust MDP safe return estimation · Single-state Bellman update, uniform Dirichlet priorexpected regretImproved
Use BCI instead of Hoeffding ambiguity setsrobust MDP safe return estimation · Single-state Bellman update, informative Gaussian priorexpected regretImproved
Use RSVF instead of BCI to construct value-adapted ambiguity setsBayesian robust MDP safe return estimation · Single-state Bellman update, informative Gaussian priorexpected regretImproved
Use BCI instead of Hoeffding ambiguity setsrobust MDP safe return estimation · RiverSwim, uninformative priorexpected regretImproved
Use RSVF instead of BCI to construct value-adapted ambiguity setsBayesian robust MDP safe return estimation · RiverSwim, uninformative priorexpected regretImproved
Use BCI instead of Hoeffding ambiguity setsrobust MDP safe return estimation · ExpPopulation, informative priorexpected regretImproved
Use RSVF instead of BCI to construct value-adapted ambiguity setsBayesian robust MDP safe return estimation · ExpPopulation, informative priorexpected regretImproved
Use the mean transition model instead of robust ambiguity setssafe return estimation · Single-state Bellman updateexpected regretMixed
Use RSVF with value-adapted sets instead of a confidence-region methodrobust MDP safe return estimation · RiverSwim, uninformative priorsafety violation rate: 0%No clear effect
Use RSVF rather than BCI or Hoeffding for the single-state Bellman updaterobust MDP safe return estimation · Single-state Bellman update, uniform Dirichlet priorsafety violation rate: 0% -> 5%Mixed

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