{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:22:43Z","timestamp":1730204563675,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9030194","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T04:43:11Z","timestamp":1584074591000},"page":"1842-1849","source":"Crossref","is-referenced-by-count":2,"title":["Potential-Based Advice for Stochastic Policy Learning"],"prefix":"10.1109","author":[{"given":"Baicen","family":"Xiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhaskar","family":"Ramasubramanian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hannaneh","family":"Hajishirzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linda","family":"Bushnell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radha","family":"Poovendran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619440"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref31"},{"key":"ref30","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref36"},{"key":"ref35","first-page":"3762","article-title":"Belief reward shaping in reinforcement learning","author":"marom","year":"2018","journal-title":"AAAI"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref10","first-page":"5","article-title":"Combining manual feedback with subsequent MDP reward signals for reinforcement learning","author":"knox","year":"2010","journal-title":"Autonomous Agents and Multiagent Systems"},{"key":"ref11","article-title":"Curiositydriven exploration by self-supervised prediction","author":"pathak","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref12","article-title":"# Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/09540099108946587"},{"key":"ref14","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1190"},{"key":"ref18","first-page":"2652","article-title":"Expressing arbitrary reward functions as potential-based advice","author":"harutyunyan","year":"2015","journal-title":"AAAI"},{"key":"ref19","first-page":"1992","article-title":"Introspective reinforcement learning and learning from demonstration","author":"li","year":"2018","journal-title":"Autonomous Agents and Multiagent Systems"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref28"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref27"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"International Conference on Machine Learning"},{"key":"ref29","first-page":"1352","article-title":"Reinforcement Learning with Deep Energy-Based Policies","author":"haarnoja","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","author":"randl\u00f8v","year":"1998","journal-title":"International Conference on Machine Learning"},{"key":"ref8","first-page":"433","article-title":"Dynamic potential-based reward shaping","author":"devlin","year":"2012","journal-title":"Autonomous Agents and Multiagent Systems"},{"key":"ref7","first-page":"792","article-title":"Principled methods for advising reinforcement learning agents","author":"wiewiora","year":"2003","journal-title":"International Conference on Machine Learning"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref9","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","author":"thomaz","year":"2006","journal-title":"AAAI"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref20","first-page":"604","article-title":"Potential-based shaping in model-based RL","author":"asmuth","year":"2008","journal-title":"AAAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9292-6"},{"key":"ref21","first-page":"565","article-title":"Reward shaping in episodic reinforcement learning","author":"grzes","year":"2017","journal-title":"Autonomous Agents and Multiagent Syst"},{"key":"ref24","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref23","article-title":"RL applied to linear quadratic regulation","author":"bradtke","year":"1993","journal-title":"Advances in neural information processing systems"},{"article-title":"Openai Gym","year":"2016","author":"brockman","key":"ref26"},{"key":"ref25","article-title":"Reinforcement learning for control: Performance, stability, and deep approximators","author":"bus\u00b8oniu","year":"2018","journal-title":"Annual Reviews in Control"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","start":{"date-parts":[[2019,12,11]]},"location":"Nice, France","end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09030194.pdf?arnumber=9030194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:25:46Z","timestamp":1658262346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9030194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9030194","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}