{"id":"https://openalex.org/W4416684053","doi":"https://doi.org/10.1007/978-981-95-4972-6_32","title":"Guardrail Guided Policy Optimisation: Learning Disentangled Safety Constraints","display_name":"Guardrail Guided Policy Optimisation: Learning Disentangled Safety Constraints","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W4416684053","doi":"https://doi.org/10.1007/978-981-95-4972-6_32"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-4972-6_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4972-6_32","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114225435","display_name":"Jaymari Chua","orcid":"https://orcid.org/0009-0008-4900-2660"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jaymari Chua","raw_affiliation_strings":["CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia"],"raw_orcid":"https://orcid.org/0009-0008-4900-2660","affiliations":[{"raw_affiliation_string":"CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337560","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0002-3119-4763"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3119-4763","affiliations":[{"raw_affiliation_string":"CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064683660","display_name":"Liming Zhu","orcid":"https://orcid.org/0000-0001-5839-3765"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liming Zhu","raw_affiliation_strings":["CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5839-3765","affiliations":[{"raw_affiliation_string":"CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"CSIRO\u2019s Data61, Australian Technology Park, 13 Garden Street, Eveleigh, NSW, 2015, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"University of New South Wales, UNSW Sydney, Kensington, NSW, 2052, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114225435"],"corresponding_institution_ids":["https://openalex.org/I31746571","https://openalex.org/I42894916"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33998075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"414","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.33649998903274536,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.33649998903274536,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08229999989271164,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07959999889135361,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7573000192642212},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6471999883651733},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6215999722480774},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5839999914169312},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5313000082969666},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.3659000098705292},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3427000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137000203132629},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7573000192642212},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6471999883651733},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5313000082969666},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C173404611","wikidata":"https://www.wikidata.org/wiki/Q528588","display_name":"Constraint programming","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-4972-6_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4972-6_32","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W3034723486","https://openalex.org/W3207474612"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-27T00:00:00"}
