Academic Journal
Inverse reinforcement learning through logic constraint inference
العنوان: | Inverse reinforcement learning through logic constraint inference |
---|---|
المؤلفون: | Baert, Mattijs, Leroux, Sam, Simoens, Pieter |
المصدر: | MACHINE LEARNING ; ISSN: 0885-6125 ; ISSN: 1573-0565 |
سنة النشر: | 2023 |
المجموعة: | Ghent University Academic Bibliography |
مصطلحات موضوعية: | Technology and Engineering, Inductive logic programming, Inverse reinforcement learning, Answer set, programming, Constraint inference, Constrained Markov decision process |
الوصف: | 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. |
نوع الوثيقة: | article in journal/newspaper |
وصف الملف: | application/pdf |
اللغة: | English |
Relation: | https://biblio.ugent.be/publication/01GY7B1ZFV9DQE5XXVTXZ5KR3H; https://biblio.ugent.be/publication/01GY7B1ZFV9DQE5XXVTXZ5KR3H/file/01GY7B3EF03W4E4TP1YWZN1FHH |
DOI: | 10.1007/s10994-023-06311-2 |
الاتاحة: | https://biblio.ugent.be/publication/01GY7B1ZFV9DQE5XXVTXZ5KR3H http://hdl.handle.net/1854/LU-01GY7B1ZFV9DQE5XXVTXZ5KR3H https://doi.org/10.1007/s10994-023-06311-2 https://biblio.ugent.be/publication/01GY7B1ZFV9DQE5XXVTXZ5KR3H/file/01GY7B3EF03W4E4TP1YWZN1FHH |
Rights: | No license (in copyright) ; info:eu-repo/semantics/openAccess |
رقم الانضمام: | edsbas.54FAFF82 |
قاعدة البيانات: | BASE |
DOI: | 10.1007/s10994-023-06311-2 |
---|