Principal-Agent Reinforcement Learning

Abstract

Contracts are the economic framework which allows a principal to delegate a task to an agent -- despite misaligned interests, and even without directly observing the agent's actions. In many modern reinforcement learning settings, self-interested agents learn to perform a multi-stage task delegated to them by a principal. We explore the significant potential of utilizing contracts to incentivize the agents. We model the delegated task as an MDP, and study a stochastic game between the principal and agent where the principal learns what contracts to use, and the agent learns an MDP policy in response. We present a learning-based algorithm for optimizing the principal's contracts, which provably converges to the subgame-perfect equilibrium of the principal-agent game. A deep RL implementation allows us to apply our method to very large MDPs with unknown transition dynamics. We extend our approach to multiple agents, and demonstrate its relevance to resolving a canonical sequential social dilemma with minimal intervention to agent rewards.