AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Efficient Multiagent Planning via Shared Action Suggestions

Dylan M. Asmar, Mykel J. Kochenderfer

AAAI 2026 · Reinforcement learning › MDPs and planning · approach: POMDP policy 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
use alpha vector indices for belief subspace refinement instead of action only (ablation)MCAS · Meet 27 UI, WPreward: 1.6 -> 2.0Improved
use alpha vector indices instead of action only (ablation)MCAS · Mars Rover UI (2 agents)reward: 19.8 -> 23.9Improved
use alpha vector indices instead of action only (ablation)MCAS · Mars Rover 5G, UIreward: 18.0 -> 20.7Improved
use alpha vector indices instead of action only (ablation)MCAS · Box Push SOreward: 199.8 -> 203.2Improved
use alpha vector indices instead of action only (ablation)MCAS · Dec-Tiger (2 agents)reward: 58.5 -> 58.5No clear effect
alpha vector indices shrink max belief set size (ablation)MCAS · Box Push SOmax belief set size: 192.1 -> 4.8Improved
alpha vector indices shrink max belief set size (ablation)MCAS · Meet 27 UI, WPmax belief set size: 16.8 -> 1.5Improved
share observations (MPOMDP) rather than control with individual observations onlyMPOMDP-I · Meet 3x3 AG, UI, WP (3 agents)reward: 1.0 -> 6.4Improved
share observations (MPOMDP) rather than individual observations onlyMPOMDP-I · Wireless (2 agents)reward: -152.8 -> -152.8No clear effect
share observations (MPOMDP) rather than individual onlyMPOMDP-I · Broadcast (2 agents)reward: 9.4 -> 9.4No clear effect
conflate true individual beliefs (MPOMDP-C) instead of centralized beliefMPOMDP · Dec-Tiger (2 agents)reward: 59.5 -> 59.5No clear effect
MCAS action-suggestion communication versus independent executionIndependent · Dec-Tiger (2 agents)reward: -68.1 -> 58.5Improved

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