AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Model and Reinforcement Learning for Markov Games with Risk Preferences

Wenjie Huang, Viet Hai Pham, William Benjamin Haskell

AAAI 2020 · Optimization › Nonconvex and smooth optimization · approach: Equilibrium learning in zero-sum games

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 CVaR risk preferences for both players instead of risk-neutral preferencesQueuing game, service provider · Queuing game, α¹=α²=0.1mean cost: -22.22 -> -77.78Improved
Use CVaR risk preferences for both players instead of risk-neutral preferencesQueuing game, router · Queuing game, α¹=α²=0.1mean cost: 37.48 -> 83.68Hurt
Use CVaR risk preferences for both players instead of risk-neutral preferencesQueuing game, system total · Queuing game, α¹=α²=0.1mean cost: 15.26 -> 5.9Improved
Use CVaR risk preferences for both players instead of risk-neutral preferencesQueuing game, service provider · Queuing game, α¹=α²=0.1variance: 1.4736e-06 -> 407.84Hurt
Use CVaR risk preferences for both players instead of risk-neutral preferencesQueuing game, router · Queuing game, α¹=α²=0.1variance: 7.32 -> 491.20Hurt
Use RaNashQL instead of Nash Q-learningQueuing game · Experiment Iconvergence rateHurt
Use RaNashQL instead of an interior point algorithmRisk-aware Markov equilibrium computation · Queuing game, state-transition-only riskruntime (seconds): 10471.975 -> 5122.657Improved
Use RaNashQL for equilibrium computationRisk-aware Markov equilibrium · Queuing game, state-transition-only riskrelative error: lower than 25%Improved

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