{"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/boredom-driven-curious-learning-by-homeo","title":"Boredom-driven curious learning by Homeo-Heterostatic Value Gradients","arxiv_id":"1806.01502","date":"2018-06-05","proceeding":null,"authors":["Yen Yu","Acer Y. C. Chang","Ryota Kanai"],"abstract":"This paper presents the Homeo-Heterostatic Value Gradients (HHVG) algorithm\nas a formal account on the constructive interplay between boredom and curiosity\nwhich gives rise to effective exploration and superior forward model learning.\nWe envisaged actions as instrumental in agent's own epistemic disclosure. This\nmotivated two central algorithmic ingredients: devaluation and devaluation\nprogress, both underpin agent's cognition concerning intrinsically generated\nrewards. The two serve as an instantiation of homeostatic and heterostatic\nintrinsic motivation. A key insight from our algorithm is that the two\nseemingly opposite motivations can be reconciled---without which exploration\nand information-gathering cannot be effectively carried out. We supported this\nclaim with empirical evidence, showing that boredom-enabled agents consistently\noutperformed other curious or explorative agent variants in model building\nbenchmarks based on self-assisted experience accumulation.","url_abs":"http://arxiv.org/abs/1806.01502v1","url_pdf":"http://arxiv.org/pdf/1806.01502v1.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":"boredom-driven-curious-learning-by-homeo","repo_url":"https://github.com/uclyyu/BoredomCuriosity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}