AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Fast Algorithms for $L_\infty$-constrained S-rectangular Robust MDPs

Bahram Behzadian, Marek Petrik, Chin Pang Ho

NeurIPS 2021 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 0 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
replace Gurobi LP with homotopy Algorithm 1SA-rectangular L-inf RMDP · Machine Replacementtime (ms): 2960 -> < 1Improved
replace Gurobi LP with homotopy Algorithm 1SA-rectangular L-inf RMDP · RiverSwimtime (ms): 2240 -> 3Improved
replace Gurobi LP with homotopy Algorithm 1SA-rectangular L-inf RMDP · Inventory Managementtime (ms): 9770 -> 10Improved
replace Gurobi LP with bisection Algorithm 2S-rectangular L-inf RMDP · Machine Replacementtime (ms): 129 -> 40Improved
replace Gurobi LP with bisection Algorithm 2S-rectangular L-inf RMDP · RiverSwimtime (ms): 217 -> 52Improved
replace Gurobi LP with bisection Algorithm 2S-rectangular L-inf RMDP · Inventory Managementtime (ms): 2740 -> 67Improved
scale number of states to a few hundredhomotopy and bisection algorithms vs Gurobi · Inventory Management relative runtimerelative time: about 100 times fasterImproved
change ambiguity set from L1 to L-infSA-rectangular RMDP with fast algorithm · Inventory Managementtime (ms): 1 -> 10Hurt
change ambiguity set from L1 to L-infS-rectangular RMDP with fast algorithm · Inventory Managementtime (ms): 5 -> 67Hurt
vary robustness budget kappaproposed algorithms · Inventory Managementcomputation timeNo clear effect
change ambiguity set from L-inf to L1 for Gurobi LPS-rectangular RMDP · Inventory Managementtime (ms): 2740 -> 2260Improved

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