{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/safety-aware-apprenticeship-learning","title":"Safety-Aware Apprenticeship Learning","arxiv_id":"1710.07983","date":"2017-10-22","proceeding":null,"authors":["Weichao Zhou","Wenchao Li"],"abstract":"Apprenticeship learning (AL) is a kind of Learning from Demonstration\ntechniques where the reward function of a Markov Decision Process (MDP) is\nunknown to the learning agent and the agent has to derive a good policy by\nobserving an expert's demonstrations. In this paper, we study the problem of\nhow to make AL algorithms inherently safe while still meeting its learning\nobjective. We consider a setting where the unknown reward function is assumed\nto be a linear combination of a set of state features, and the safety property\nis specified in Probabilistic Computation Tree Logic (PCTL). By embedding\nprobabilistic model checking inside AL, we propose a novel\ncounterexample-guided approach that can ensure safety while retaining\nperformance of the learnt policy. We demonstrate the effectiveness of our\napproach on several challenging AL scenarios where safety is essential.","url_abs":"http://arxiv.org/abs/1710.07983v4","url_pdf":"http://arxiv.org/pdf/1710.07983v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"safety-aware-apprenticeship-learning","repo_url":"https://github.com/zwc662/CAV2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}