Principal-Agent Reinforcement Learning
Ivanov, Dima, Dütting, Paul, Talgam-Cohen, Inbal, Wang, Tonghan, Parkes, David C.
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jul-25-2024
- Country:
- North America > United States
- New York (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Europe
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Greater London > London (0.04)
- Switzerland > Zürich
- Zürich (0.14)
- United Kingdom > England
- Asia > Middle East
- Jordan (0.04)
- Israel > Haifa District
- Haifa (0.04)
- North America > United States
- Genre:
- Research Report > New Finding (0.92)
- Industry:
- Education (0.67)
- Leisure & Entertainment > Games (0.67)