AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

Silviu Pitis

NeurIPS 2023 · Multi-agent systems and games › Games and equilibria · approach: Learning with strategic agents · 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
Aggregate work and play rewards using fixed Markovian weights despite their different discount factorsWork/play objectives in Procrastinator's Peril · Procrastinator's Periltrajectory value: 3.20 vs 1.00Mixed
Use history-dependent aggregation weights updated by each objective's discount factorMulti-objective aggregation · Procrastinator's Periltrajectory value: 3.00 -> 3.20Improved
Increase historical discounting factor from η=0.00 to η=1.00Historical discounting · Procrastinator's Peril with shifting preferencesfirst-step discounted reward: 2.635 -> 3.200Improved
Use historical discounting with η=0.30 rather than η=0.00Historical discounting · Procrastinator's Peril with shifting preferencesfirst-step discounted reward: 2.635 -> 2.635No clear effect
Use fixed Markovian stationary-policy optimization instead of a history-dependent policyProcrastinator's Peril · Procrastinator's Periltrajectory value: 3.2 -> 3.0Hurt

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