Inverse reinforcement learning through logic constraint inference

Abstract

Autonomous robots start to be integrated in human environments where explicit and implicit social norms guide the behavior of all agents. To assure safety and predictability, these artificial agents should act in accordance with the applicable social norms. However, it is not straightforward to define these rules and incorporate them in an agent's policy. Particularly because social norms are often implicit and environment specific. In this paper, we propose a novel iterative approach to extract a set of rules from observed human trajectories. This hybrid method combines the strengths of inverse reinforcement learning and inductive logic programming. We experimentally show how our method successfully induces a compact logic program which represents the behavioral constraints applicable in a Tower of Hanoi and a traffic simulator environment. The induced program is adopted as prior knowledge by a model-free reinforcement learning agent to speed up training and prevent any social norm violation during exploration and deployment. Moreover, expressing norms as a logic program provides improved interpretability, which is an important pillar in the design of safe artificial agents, as well as transferability to similar environments.

Norm Augmented Reinforcement Learning Agents With Synthesized Normative Rules

“…The constraint inference process model (Baert et al, 2023) uses inverse reinforcement learning (IRL) to extract normative rules. As the agent learns from IRL using inductive logic programming, it abstracts knowledge into hypotheses represented by positive and negative hypotheses in the form of answer set programming.…”