{"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/visceral-machines-reinforcement-learning-with","title":"Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological Rewards","arxiv_id":"1805.09975","date":"2018-05-25","proceeding":null,"authors":["Daniel McDuff","Ashish Kapoor"],"abstract":"As people learn to navigate the world, autonomic nervous system (e.g., \"fight\nor flight\") responses provide intrinsic feedback about the potential\nconsequence of action choices (e.g., becoming nervous when close to a cliff\nedge or driving fast around a bend.) Physiological changes are correlated with\nthese biological preparations to protect one-self from danger. We present a\nnovel approach to reinforcement learning that leverages a task-independent\nintrinsic reward function trained on peripheral pulse measurements that are\ncorrelated with human autonomic nervous system responses. Our hypothesis is\nthat such reward functions can circumvent the challenges associated with sparse\nand skewed rewards in reinforcement learning settings and can help improve\nsample efficiency. We test this in a simulated driving environment and show\nthat it can increase the speed of learning and reduce the number of collisions\nduring the learning stage.","url_abs":"http://arxiv.org/abs/1805.09975v2","url_pdf":"http://arxiv.org/pdf/1805.09975v2.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":"visceral-machines-reinforcement-learning-with","repo_url":"https://github.com/microsoft/affect_based_intrinsic_rewards_for_learning_representations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"visceral-machines-reinforcement-learning-with","repo_url":"https://github.com/microsoft/affectbased","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}