AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Collaborative Decision Making Using Action Suggestions

Dylan Asmar, Mykel Kochenderfer

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Human-AI coordination agents · 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 scaled-rational suggestion update (τ=0.99) vs no suggestionsPOMDP agent · Tagmean reward: -10.7 -> -1.8Improved
add noisy-rational suggestion update (λ=5.0) vs no suggestionsPOMDP agent · RockSample(7,8,20,0)mean reward: 21.5 -> 27.5Improved
belief-update with suggestion (scaled τ=0.99) instead of naively following (ν=1.00)POMDP agent · RockSample(7,8,20,0)number of suggestions: 15.3 -> 6.4Improved
belief-update with suggestion (scaled τ=0.99) instead of naively following (ν=1.00)POMDP agent · RockSample(8,4,10,-1)number of suggestions: 8.4 -> 2.8Improved
belief-update with suggestion (scaled τ=0.99) instead of naively following (ν=1.00)POMDP agent · Tagmean reward: -1.6 -> -1.8No clear effect
lower naive follow rate ν from 1.00 to 0.50Naive agent · Tagmean reward: -1.6 -> -6.8Hurt
lower naive follow rate ν from 1.00 to 0.50Naive agent · Tagnumber of suggestions: 3.7 -> 15.2Hurt
lower trust τ from 0.99 to 0.50 (ablation)Scaled agent · Tagmean reward: -1.8 -> -3.6Hurt
lower trust τ from 0.99 to 0.50 (ablation)Scaled agent · RockSample(8,4,10,-1)mean reward: 16.4 -> 16.3No clear effect
lower λ from 5.0 to 1.0 (ablation)Noisy agent · Tagmean reward: -1.8 -> -2.4Hurt
lower λ from 5.0 to 1.0 (ablation)Noisy agent · RockSample(7,8,20,0)number of suggestions: 7.8 -> 10.6Hurt
increase randomness of suggester from perfect to fully randomNaive agent · Tag and RockSample(8,4,10,-1)mean rewardHurt

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