Modelling Bounded Rationality In Multi-agent Interactions By Generalized Recursive Reasoning

Abstract

Though limited in real-world decision making, most multi-agent reinforcement learning (MARL) models assume perfectly rational agents -- a property hardly met due to individual's cognitive limitation and/or the tractability of the decision problem. In this paper, we introduce generalized recursive reasoning (GR2) as a novel framework to model agents with different *hierarchical* levels of rationality; our framework enables agents to exhibit varying levels of "thinking" ability thereby allowing higher-level agents to best respond to various less sophisticated learners. We contribute both theoretically and empirically. On the theory side, we devise the hierarchical framework of GR2 through probabilistic graphical models and prove the existence of a perfect Bayesian equilibrium. Within the GR2, we propose a practical actor-critic solver, and demonstrate its convergent property to a stationary point in two-player games through Lyapunov analysis. On the empirical side, we validate our findin

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keywen2019modelling

Related papers

• Probabilistic Recursive Reasoning For Multi-agent Reinforcement Learning (2019)0.00
• Learning And Calibrating Heterogeneous Bounded Rational Market Behaviour With Multi-agent Reinforcement Learning (2024)0.00
• Iterated Reasoning With Mutual Information In Cooperative And Byzantine Decentralized Teaming (2022)0.00
• Breaking The Curse Of Multiagency In Robust Multi-agent Reinforcement Learning (2024)0.00
• Understanding Individual Decision-making In Multi-agent Reinforcement Learning: A Dynamical Systems Approach (2025)0.00
• Remembering The Markov Property In Cooperative MARL (2025)0.00
• Probing Dec-pomdp Reasoning In Cooperative MARL (2026)0.00
• Negotiated Reasoning: On Provably Addressing Relative Over-generalization (2023)0.00