{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:53Z","timestamp":1758672893818,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Abstraction is a critical technique in general problem-solving, allowing complex tasks to be decomposed into smaller, manageable sub-tasks. While traditional symbolic planning relies on predefined primitive symbols to construct structured abstractions, its reliance on formal representations limits applicability to real-world tasks. On the other hand, reinforcement learning excels at learning end-to-end policies directly from sensory inputs in unstructured environments but struggles with compositional generalization in complex tasks with delayed rewards. In this paper, we propose Abductive Abstract Reinforcement Learning (A2RL), a novel neuro-symbolic RL framework bridging the two paradigms based on Abductive Learning (ABL), enabling RL agents to learn abstractions directly from raw sensory inputs without predefined symbols.\n\nA2RL induces a finite state machine to represent high-level, step-by-step procedures, where each abstract state corresponds to a sub-algebra of the original Markov Decision Process (MDP). This approach not only bridges the gap between symbolic abstraction and sub-symbolic learning but also provides a natural mechanism for the emergence of new symbols. Experiments show that A2RL can mitigate the delayed reward problem and improve the generalization capability compared to traditional end-to-end RL methods.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/725","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"6515-6523","source":"Crossref","is-referenced-by-count":0,"title":["From End-to-end to Step-by-step: Learning to Abstract via Abductive Reinforcement Learning"],"prefix":"10.24963","author":[{"given":"Zilong","family":"Wang","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University"},{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiongda","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences"},{"name":"University of Chinese Academy of Sciences, School of Future Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ZhiPeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University"},{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianming","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang-Zhou","family":"Dai","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University"},{"name":"School of Intelligence Science and Technology, Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:34:58Z","timestamp":1758627298000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/725"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/725","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}