{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:14:39Z","timestamp":1755800079526,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,26]]},"DOI":"10.1109\/cog64752.2025.11114355","type":"proceedings-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:06:42Z","timestamp":1755626802000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Fast: Similarity-Based Knowledge Transfer for Efficient Policy Learning"],"prefix":"10.1109","author":[{"given":"Alessandro","family":"Capurso","sequence":"first","affiliation":[{"name":"University of Pisa,Department of Computer Science,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elia","family":"Piccoli","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Davide","family":"Bacciu","sequence":"additional","affiliation":[{"name":"University of Pisa,Department of Computer Science,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref2","article-title":"Playing Atari with Deep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref4","article-title":"Soft Actor-Critic: OffPolicy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"Haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref5","article-title":"Distilling the Knowledge in a Neural Network","author":"Hinton","year":"2015","journal-title":"CoRR"},{"key":"ref6","article-title":"Policy Distillation","author":"Rusu","year":"2016","journal-title":"ICLR"},{"key":"ref7","article-title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","author":"Parisotto","year":"2016","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref9","article-title":"Progress & Compress: A scalable framework for continual learning","author":"Schwarz","year":"2018","journal-title":"ICML"},{"key":"ref10","article-title":"Multi-Task Reinforcement Learning with Soft Modularization","author":"Yang","year":"2020","journal-title":"NeurIPS"},{"key":"ref11","article-title":"A Survey of Meta-Reinforcement Learning","author":"Beck","year":"2023","journal-title":"CoRR"},{"key":"ref12","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","author":"Finn","year":"2017","journal-title":"ICML"},{"key":"ref13","article-title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","author":"Zintgraf","year":"2019","journal-title":"ICLR"},{"key":"ref14","article-title":"Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning","author":"Isele","year":"2016","journal-title":"IJCAI\/AAAI Press"},{"key":"ref15","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2021","journal-title":"CoRL"},{"key":"ref16","article-title":"Skill-based metareinforcement learning","author":"Nam","year":"2022","journal-title":"ICLR"},{"key":"ref17","article-title":"Skill-based Model-based Reinforcement Learning","author":"Shi","year":"2022","journal-title":"CoRL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2014.7004683"},{"key":"ref19","article-title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","author":"Ahn","year":"2022","journal-title":"CoRL"},{"key":"ref20","article-title":"Learning Inter-Task Transferability in the Absence of Target Task Samples","author":"Sinapov","year":"2015","journal-title":"AAMAS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645586"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_23"},{"key":"ref23","article-title":"Building a subspace of policies for scalable continual learning","author":"Gaya","year":"2023","journal-title":"ICLR"},{"key":"ref24","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref25","article-title":"Stablebaselines3: Reliable reinforcement learning implementations","author":"Raffin","year":"2021","journal-title":"JMLR"},{"key":"ref26","article-title":"An environment for autonomous driving decision-making","author":"Leurent","year":"2018","journal-title":"GitHub repository"},{"key":"ref27","article-title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","author":"Towers","year":"2024","journal-title":"CoRR"}],"event":{"name":"2025 IEEE Conference on Games (CoG)","start":{"date-parts":[[2025,8,26]]},"location":"Lisbon, Portugal","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11113832\/11113841\/11114355.pdf?arnumber=11114355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T06:26:50Z","timestamp":1755671210000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11114355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cog64752.2025.11114355","relation":{},"subject":[],"published":{"date-parts":[[2025,8,26]]}}}