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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use CVaR risk preferences for both players instead of risk-neutral preferences | Queuing game, service provider · Queuing game, α¹=α²=0.1 | mean cost: -22.22 -> -77.78 | Improved |
| Use CVaR risk preferences for both players instead of risk-neutral preferences | Queuing game, router · Queuing game, α¹=α²=0.1 | mean cost: 37.48 -> 83.68 | Hurt |
| Use CVaR risk preferences for both players instead of risk-neutral preferences | Queuing game, system total · Queuing game, α¹=α²=0.1 | mean cost: 15.26 -> 5.9 | Improved |
| Use CVaR risk preferences for both players instead of risk-neutral preferences | Queuing game, service provider · Queuing game, α¹=α²=0.1 | variance: 1.4736e-06 -> 407.84 | Hurt |
| Use CVaR risk preferences for both players instead of risk-neutral preferences | Queuing game, router · Queuing game, α¹=α²=0.1 | variance: 7.32 -> 491.20 | Hurt |
| Use RaNashQL instead of Nash Q-learning | Queuing game · Experiment I | convergence rate | Hurt |
| Use RaNashQL instead of an interior point algorithm | Risk-aware Markov equilibrium computation · Queuing game, state-transition-only risk | runtime (seconds): 10471.975 -> 5122.657 | Improved |
| Use RaNashQL for equilibrium computation | Risk-aware Markov equilibrium · Queuing game, state-transition-only risk | relative error: lower than 25% | Improved |
Closest papers by meaning
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.88)
- Planning and Learning in Average Risk-aware MDPs (NeurIPS 2025 · similarity 0.87)
- Risk-Averse Total-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.87)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.87)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.87)
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.
