Learning Approximately Optimal Contracts
This work addresses contract design in principal-agent models for economics and AI, offering a novel learning approach but is incremental as it builds on classical theory with extensions to risk aversion.
The paper tackles the problem of a principal learning optimal contracts without knowing the agent's utility or action space, by sequentially offering contracts to identical agents and observing outcomes. It presents an algorithm that bounds the number of samples needed to achieve a contract within ε of optimal net profit, with results robust to risk-averse agents and aligning with classical theory in specific cases.
In principal-agent models, a principal offers a contract to an agent to perform a certain task. The agent exerts a level of effort that maximizes her utility. The principal is oblivious to the agent's chosen level of effort, and conditions her wage only on possible outcomes. In this work, we consider a model in which the principal is unaware of the agent's utility and action space: she sequentially offers contracts to identical agents, and observes the resulting outcomes. We present an algorithm for learning the optimal contract under mild assumptions. We bound the number of samples needed for the principal to obtain a contract that is within $\eps$ of her optimal net profit for every $\eps>0$. Our results are robust even when considering risk-averse agents. Furthermore, we show that when there are only two possible outcomes or the agent is risk-neutral, the algorithm's outcome approximates the optimal contract described in the classical theory.