{"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/factorized-machine-self-confidence-for","title":"Factorized Machine Self-Confidence for Decision-Making Agents","arxiv_id":"1810.06519","date":"2018-10-15","proceeding":null,"authors":["Brett W. Israelsen","Nisar R. Ahmed","Eric Frew","Dale Lawrence","Brian Argrow"],"abstract":"Algorithmic assurances from advanced autonomous systems assist human users in\nunderstanding, trusting, and using such systems appropriately. Designing these\nsystems with the capacity of assessing their own capabilities is one approach\nto creating an algorithmic assurance. The idea of `machine self-confidence' is\nintroduced for autonomous systems. Using a factorization based framework for\nself-confidence assessment, one component of self-confidence, called\n`solver-quality', is discussed in the context of Markov decision processes for\nautonomous systems. Markov decision processes underlie much of the theory of\nreinforcement learning, and are commonly used for planning and decision making\nunder uncertainty in robotics and autonomous systems. A `solver quality' metric\nis formally defined in the context of decision making algorithms based on\nMarkov decision processes. A method for assessing solver quality is then\nderived, drawing inspiration from empirical hardness models. Finally, numerical\nexperiments for an unmanned autonomous vehicle navigation problem under\ndifferent solver, parameter, and environment conditions indicate that the\nself-confidence metric exhibits the desired properties. Discussion of results,\nand avenues for future investigation are included.","url_abs":"http://arxiv.org/abs/1810.06519v2","url_pdf":"http://arxiv.org/pdf/1810.06519v2.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":"factorized-machine-self-confidence-for","repo_url":"https://github.com/COHRINT/FaMSeC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":null}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"decision-making-under-uncertainty","task_name":"Decision Making Under Uncertainty"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}