{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:07:20Z","timestamp":1755796040287,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,5]]},"DOI":"10.1109\/cog60054.2024.10645586","type":"proceedings-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T18:44:09Z","timestamp":1724870649000},"page":"1-4","source":"Crossref","is-referenced-by-count":1,"title":["I Know How: Combining Prior Policies to Solve New Tasks"],"prefix":"10.1109","author":[{"given":"Malio","family":"Li","sequence":"first","affiliation":[{"name":"University of Pisa,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elia","family":"Piccoli","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincenzo","family":"Lomonaco","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Bacciu","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"04671","key":"ref1","volume-title":"Progressive neural networks arXiv preprint arXiv","volume":"1606","author":"Rusu","year":"2016"},{"key":"ref2","article-title":"Progress & compress: A scalable framework for continual learning","author":"Schwarz","year":"2018","journal-title":"ICML"},{"key":"ref3","article-title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","author":"Veniat","year":"2021","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"issue":"11289","key":"ref5","volume-title":"Learning to Compose Skills arXiv preprint arXiv","volume":"1711","author":"Sahni","year":"2017"},{"key":"ref6","article-title":"Distral: Robust multitask reinforcement learning","author":"Teh","year":"2017","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2021","journal-title":"CoRL"},{"key":"ref8","article-title":"Skill-based meta-reinforcement learning","author":"Nam","year":"2022","journal-title":"ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179268"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01214"},{"key":"ref12","article-title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","author":"Florensa","year":"2017","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4275623"},{"key":"ref14","article-title":"Towards applicable P. reinfcement learning: Impr oving the generalization and sample efficiency with policy ensemble","author":"Yang","year":"2022","journal-title":"IJCAI"},{"key":"ref15","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref16","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","author":"Raffin","year":"2021","journal-title":"JMLR"},{"key":"ref17","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018","journal-title":"GitHub repository"},{"key":"ref18","article-title":"Building a subspace of policies for scalable continual learning","author":"Gaya","year":"2023","journal-title":"ICLR"}],"event":{"name":"2024 IEEE Conference on Games (CoG)","start":{"date-parts":[[2024,8,5]]},"location":"Milan, Italy","end":{"date-parts":[[2024,8,8]]}},"container-title":["2024 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10645493\/10645533\/10645586.pdf?arnumber=10645586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T10:41:05Z","timestamp":1725446465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10645586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/cog60054.2024.10645586","relation":{},"subject":[],"published":{"date-parts":[[2024,8,5]]}}}