Mechanisms For A No-regret Agent: Beyond The Common Prior

Abstract

A rich class of mechanism design problems can be understood as incomplete-information games between a principal who commits to a policy and an agent who responds, with payoffs determined by an unknown state of the world. Traditionally, these models require strong and often-impractical assumptions about beliefs (a common prior over the state). In this paper, we dispense with the common prior. Instead, we consider a repeated interaction where both the principal and the agent may learn over time from the state history. We reformulate mechanism design as a reinforcement learning problem and develop mechanisms that attain natural benchmarks without any assumptions on the state-generating process. Our results make use of novel behavioral assumptions for the agent -- centered around counterfactual internal regret -- that capture the spirit of rationality without relying on beliefs.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycamara2020mechanisms

Related papers

• Learning A Game By Paying The Agents (2025)0.00
• Pessimism Meets VCG: Learning Dynamic Mechanism Design Via Offline Reinforcement Learning (2022)0.00
• Bounded Risk-sensitive Markov Games: Forward Policy Design And Inverse Reward Learning With Iterative Reasoning And Cumulative Prospect Theory (2020)0.00
• Distributed No-regret Learning In Multi-agent Systems (2020)0.00
• Symbol Guided Hindsight Priors For Reward Learning From Human Preferences (2022)0.00
• Taming Equilibrium Bias In Risk-sensitive Multi-agent Reinforcement Learning (2024)0.00
• Stochastic Principal-agent Problems: Efficient Computation And Learning (2023)0.00
• No-regret Learning In Unknown Games With Correlated Payoffs (2019)0.00