Multi-agent Learning In Contextual Games Under Unknown Constraints

Abstract

We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent's action needs to belong to a feasible set, but the feasible set is a priori unknown. For example, in constrained multi-agent reinforcement learning, the constraints on the agents' policies are a function of the unknown dynamics and hence, are themselves unknown. Under kernel-based regularity assumptions on the unknown functions, we develop a no-regret, no-violation approach which exploits similarities among different reward and constraint outcomes. The no-violation property ensures that the time-averaged sum of constraint violations converges to zero as the game is repeated. We show that our algorithm, referred to as c.z.AdaNormalGP, obtains kernel-dependent regret bounds and that the cumulative constraint violations have sublinear kernel-dependent upper bounds. In addition we introduce the notion of constrained

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymaddux2023multi

Related papers

• No-regret Learning In Unknown Games With Correlated Payoffs (2019)0.00
• Distributed No-regret Learning In Multi-agent Systems (2020)0.00
• Independent Learning In Constrained Markov Potential Games (2024)0.00
• Learning A Game By Paying The Agents (2025)0.00
• Convergence Analysis Of Gradient-based Learning With Non-uniform Learning Rates In Non-cooperative Multi-agent Settings (2019)0.00
• Opponent Learning Awareness And Modelling In Multi-objective Normal Form Games (2020)7.16
• No-regret Exploration In Contextual Reinforcement Learning (2019)0.00
• Online Learning In Unknown Markov Games (2020)0.00