AI Paper Atlas

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

Multi-agent active perception with prediction rewards

Mikko Lauri, Frans Oliehoek

NeurIPS 2020 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Decentralized actor-critic MARL · 1 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
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · MAV h=2policy value: -2.112 -> -2.006Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · MAV h=3policy value: -2.002 -> -1.936Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · MAV h=4policy value: -1.943 -> -1.879Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · MAV h=5policy value: -1.918 -> -1.842Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · Rovers h=2policy value: -3.800 -> -3.484Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · Rovers h=3policy value: -3.680 -> -3.402Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · Rovers h=4policy value: -3.640 -> -3.367Improved
Add adaptive α-vector selection rather than randomly resampling α-vectors (ablation)APAS · Rovers h=5policy value: -3.591 -> -3.293Improved
Use APAS instead of NPGIMAV · MAV h=2policy value: -1.931 -> -2.006Hurt
Use APAS instead of NPGIRovers · Rovers h=2policy value: -3.495 -> -3.484Improved
Extend planning beyond horizon 5 using APAS rather than NPGIMulti-agent active perception planning · MAVmaximum completed planning horizon: h>5Improved
Increase the number of α-vectors from K=5 to K=10 (ablation)APAS · Rovers h=10policy valueNo clear effect

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