AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Decentralized Planning in Stochastic Environments with Submodular Rewards

Rajiv Kumar, Pradeep Varakantham, Akshat Kumar

AAAI 2017 · Reinforcement learning › MDPs and planning · approach: Robust MDP policy gradient

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 posteriori online bound instead of a priori 50% guaranteelazy greedy · Security gamesguarantee from optimal: 50% -> 90%Improved
use PWCSUBMOD instead of lazy greedypolicy via piecewise constant approximation · Security gamesonline guarantee: 3% less (best), 9% less (worst)Hurt
use PWCSUBMOD instead of lazy greedyPWCSUBMOD · Security gamesruntime: 12000 seconds -> a few secondsImproved
use PWCSUBMOD instead of lazy greedyPWCSUBMOD · Sensor networkruntime: 4800 seconds -> a few secondsImproved
use PWCSUBMOD instead of lazy greedyPWCSUBMOD · Sensor networksolution qualityImproved
use PWCSUBMOD instead of lazy greedyPWCSUBMOD · Sensor networkonline guaranteeNo clear effect
use lazy greedy instead of greedylazy greedy · Security gamesscalabilityImproved
raise effectiveness parameter epsilon from 0.3 to 0.7lazy greedy · Sensor network 2*2, 4 sensorsonline guarantee: 61.6 -> 76.1Improved
larger sensor network grid (10*5) at epsilon 0.7lazy greedy · Sensor networkonline guarantee: 76.1 -> 63.6Hurt

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