AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Semi-Infinitely Constrained Markov Decision Processes and Provably Efficient Reinforcement Learning

Liangyu Zhang, Peng Yang, Wenhao Yang, Zhihua Zhang

TPAMI 2024 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 11 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
solve with SI-CRL (exchange method over continuum of constraints) instead of naive discretization into a CMDPtabular CMDP solver · Discharge of Sewagesolution qualityImproved
use SI-CRL with dual simplex re-optimization instead of a single LP over a discretized gridtabular CMDP solver · Discharge of Sewagetime to reach given accuracyImproved
use SI-CRL instead of discretization baselinetabular CMDP solver · Discharge of Sewagenumber of active constraintsImproved
use SI-CPO instead of discretization baselines solved by CRPOpolicy optimization · Discharge of Sewageconvergence speedImproved
use SI-CPO instead of discretization baseline with N=1000policy optimization · Discharge of Sewagetime per iteration (s): 0.45 ± 0.04 -> 0.19 ± 0.02Improved
increase discretization grid size N_baselineCRPO baseline · Ship Route PlanningconvergenceNo clear effect
use SI-CPPO instead of discretization baselinepolicy optimization · Ship Route Planningroute feasibilityImproved
use SI-CPPO instead of discretization baseline N=250policy optimization · Ship Route Planningtime per iteration (s): 8.91 ± 1.50 -> 11.39 ± 1.43Hurt
use SI-CPPO instead of discretization baselinepolicy optimization · Ship Route PlanningconvergenceImproved

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