2024/07/31 by Colin Shea-Blymyer, Shea-Blymyer, Colin, Houssam Abbas +1 · 2 citations
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Blockchain Technology Applications and Security #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.2408.00147
openalex publication_date 2024/07/31 · openalex created_date 2024/08/04 · openalex updated_date 2026/07/28
When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually happening, and how a policy might be modified to remove the conflict. These obligations include ethical and social obligations, permissions and prohibitions, which constrain how the agent achieves its mission and executes its policy. We propose a new deontic logic, Expected Act Utilitarian deontic logic, for enabling this reasoning at design time: for specifying and verifying the agent's strategic obligations, then modifying its policy from a reference policy to meet those obligations. Unlike approaches that work at the reward level, working at the logical level increases the transparency of the trade-offs. We introduce two algorithms: one for model-checking whether an RL agent has the right strategic obligations, and one for modifying a reference decision policy to make it meet obligations expressed in our logic. We illustrate our algorithms on DAC-MDPs which accurately abstract neural decision policies, and on toy gridworld environments.