An Active Learning Method For Solving Competitive Multi-agent Decision-making And Control Problems

Abstract

To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions and recursively update simple local parametric estimates of the action-reaction mappings. Under very general working assumptions (not even assuming that a stationary profile exists), sufficient conditions are established to assess the asymptotic properties of the proposed active learning methodology so that, if the parameters characterizing the action-reaction mappings converge, a stationary action profile is achieved. Such conditions hence act also as certificates for the existence of such a profile. Extensive numerical simulations involving typical competitive multi-agent control and decision-making problems illustrate the practical effectiveness of the proposed learning-based approach.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyfabiani2022an

Related papers

• Game-theoretical Perspectives On Active Equilibria: A Preferred Solution Concept Over Nash Equilibria (2022)0.00
• A Survey Of Learning In Multiagent Environments: Dealing With Non-stationarity (2017)0.00
• Non-cooperative Multi-agent Systems With Exploring Agents (2020)0.00
• Sa-matd3:self-attention-based Multi-agent Continuous Control Method In Cooperative Environments (2021)11.76
• Moody Learners -- Explaining Competitive Behaviour Of Reinforcement Learning Agents (2020)8.09
• Actively Learning Reinforcement Learning: A Stochastic Optimal Control Approach (2023)0.00
• Understanding Individual Decision-making In Multi-agent Reinforcement Learning: A Dynamical Systems Approach (2025)0.00
• Research On Multi-agent Communication And Collaborative Decision-making Based On Deep Reinforcement Learning (2023)0.00