AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

IPOMDP-Net: A Deep Neural Network for Partially Observable Multi-Agent Planning Using Interactive POMDPs

Yanlin Han, Piotr Gmytrasiewicz

AAAI 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 12 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 model-free ADRQN with model-based IPOMDP-netagent policy network · Tiger (fixed env)average reward: 1.29 ± 0.35 -> 1.32 ± 0.29No clear effect
replace model-free ADRQN with model-based IPOMDP-netagent policy network · UAV (fixed env)average reward: 8.98 ± 0.97 -> 9.19 ± 0.72No clear effect
replace ADRQN with IPOMDP-netagent policy network · Maze 4×4average reward: 0.12 ± 0.08 -> 0.18 ± 0.05Improved
replace ADRQN with IPOMDP-netagent policy network · Maze 10×10average reward: -0.73 ± 0.17 -> -0.52 ± 0.10Improved
replace ADRQN with IPOMDP-net, transferred from 10×10 trainingagent policy network · Maze 16×16average reward: -1.58 ± 0.39 -> -0.88 ± 0.21Improved
preassign IPOMDP-net weights with true model vs symbolic I-POMDP (QMDP)IPOMDP-net · Tigeraverage reward: 2.26 ± 0.09 -> 2.25 ± 0.11No clear effect
preassign IPOMDP-net weights with true model vs symbolic I-POMDP (QMDP)IPOMDP-net · Maze 16×16average reward: -0.96 ± 0.09 -> -0.99 ± 0.10No clear effect
use SARSOP planner instead of QMDP in symbolic I-POMDPI-POMDP · Maze 16×16average reward: -0.96 ± 0.09 -> -0.81 ± 0.10Improved
use SARSOP planner instead of QMDP in symbolic I-POMDPI-POMDP · UAVaverage reward: 9.09 ± 0.45 -> 9.27 ± 0.52No clear effect
increase map size from 4×4 to 16×16ADRQN · Mazeaverage reward: 0.12 ± 0.08 -> -1.58 ± 0.39Hurt
increase map size from 4×4 to 16×16IPOMDP-net trained · Mazeaverage reward: 0.18 ± 0.05 -> -0.88 ± 0.21Hurt

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