AI Paper Atlas

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

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

Zhuodong Yu, Ling Dai, Shaohang Xu, Siyang Gao, Chin Pang Ho

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 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
Use nested-bisection Fast algorithm instead of GurobiWasserstein DRMDP Bellman update (q=1) · Random DRMDP N=S=A=40runtime (s): 22.6013 -> 0.5112Improved
Use Fast algorithm instead of first-order method FOM (3 its)Wasserstein DRMDP Bellman update (q=1) · Random DRMDP N=S=A=40runtime (s): 29.22 -> 0.5112Improved
Use Fast algorithm instead of Gurobi at smallest sizeWasserstein DRMDP Bellman update (q=1) · Random DRMDP N=S=A=10runtime (s): 0.039 -> 0.0253Improved
Use Fast algorithm instead of FOM at size 10Wasserstein DRMDP Bellman update (q=1) · Random DRMDP N=S=A=10runtime (s): 0.644 -> 0.0253Improved
Scale problem size from 10 to 40 for FastFast algorithm (q=1) · Random DRMDP N=S=Aruntime (s): 0.0253 -> 0.5112Hurt
Scale problem size from 10 to 40 for GurobiGurobi (q=1) · Random DRMDP N=S=Aruntime (s): 0.039 -> 22.6013Hurt
Use Fast algorithm instead of Gurobi at size 80 (L2)Wasserstein DRMDP Bellman update (q=2) · Random DRMDP N=S=A=80runtime (s): 44.3305 -> 24.6080Improved
Use Fast algorithm instead of FOM at size 80 (L2)Wasserstein DRMDP Bellman update (q=2) · Random DRMDP N=S=A=80runtime (s): 31.1326 -> 24.6080Improved
Use Fast algorithm instead of Gurobi at size 50 (L2)Wasserstein DRMDP Bellman update (q=2) · Random DRMDP N=S=A=50runtime (s): 5.1669 -> 7.3717Hurt
Use Fast algorithm instead of FOM at size 50 (L2)Wasserstein DRMDP Bellman update (q=2) · Random DRMDP N=S=A=50runtime (s): 9.1936 -> 7.3717Improved
Use Fast algorithm instead of Gurobi at size 60 (L2)Wasserstein DRMDP Bellman update (q=2) · Random DRMDP N=S=A=60runtime (s): 11.6760 -> 10.8293Improved

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