Learning To Steer Markovian Agents Under Model Uncertainty

Abstract

Designing incentives for an adapting population is a ubiquitous problem in a wide array of economic applications and beyond. In this work, we study how to design additional rewards to steer multi-agent systems towards desired policies *without* prior knowledge of the agents' underlying learning dynamics. Motivated by the limitation of existing works, we consider a new and general category of learning dynamics called *Markovian agents*. We introduce a model-based non-episodic Reinforcement Learning (RL) formulation for our steering problem. Importantly, we focus on learning a *history-dependent* steering strategy to handle the inherent model uncertainty about the agents' learning dynamics. We introduce a novel objective function to encode the desiderata of achieving a good steering outcome with reasonable cost. Theoretically, we identify conditions for the existence of steering strategies to guide agents to the desired policies. Complementing our theoretical contributions, we provide em

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2024learning

Related papers

• Incentivize Without Bonus: Provably Efficient Model-based Online Multi-agent RL For Markov Games (2025)0.00
• Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach (2023)0.00
• Independent Learning In Stochastic Games (2021)6.77
• Reinforcement Learning In Non-markovian Environments (2022)7.50
• Optimal Decision-making In Mixed-agent Partially Observable Stochastic Environments Via Reinforcement Learning (2019)0.00
• Minimax-optimal Multi-agent RL In Markov Games With A Generative Model (2022)2.26
• Learning In Markov Games With Adaptive Adversaries: Policy Regret, Fundamental Barriers, And Efficient Algorithms (2024)0.00
• Understanding Individual Decision-making In Multi-agent Reinforcement Learning: A Dynamical Systems Approach (2025)0.00