{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:02:01Z","timestamp":1730228521145,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"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":[[2020,2]]},"DOI":"10.1109\/icaiic48513.2020.9065237","type":"proceedings-article","created":{"date-parts":[[2020,4,17]],"date-time":"2020-04-17T01:46:17Z","timestamp":1587087977000},"page":"193-198","source":"Crossref","is-referenced-by-count":2,"title":["PPMC Training Algorithm: A Deep Learning Based Path Planner and Motion Controller"],"prefix":"10.1109","author":[{"given":"Tamir","family":"Blum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Jones","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuya","family":"Yoshida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.010"},{"journal-title":"Learning to Walk via Deep Reinforcement Learning","year":"2018","author":"haarnoja","key":"ref11"},{"journal-title":"Fast Approximate Clearance Evaluation for Rovers with Articulated Suspension Systems","year":"2018","author":"otsu","key":"ref12"},{"journal-title":"Hierarchical visuomotor control of humanoids","year":"2018","author":"merel","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"journal-title":"PRM-RL Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning","year":"2017","author":"faust","key":"ref15"},{"journal-title":"Learning Symmetry and Low-energy Locomotion","year":"2018","author":"yu","key":"ref16"},{"journal-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-25332-5_42"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SII46433.2020.9025928"},{"journal-title":"Learning Dexterous in-Hand Manipulation","year":"2018","author":"open","key":"ref4"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s40638-016-0055-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"journal-title":"Neural slam Learning to explore with external memory","year":"2017","author":"zhang","key":"ref7"},{"journal-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","year":"2017","author":"wu","key":"ref2"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"journal-title":"An investigation of model-free planning","year":"2019","author":"guez","key":"ref9"},{"key":"ref20","volume":"1","author":"thomaz","year":"2006","journal-title":"Reinforcement learning with human teachers Evidence of feedback and guidance with implications for learning performance"},{"journal-title":"Addressing Function Approximation Error in Actor-Critic Methods","year":"2018","author":"fujimoto","key":"ref22"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref21"},{"journal-title":"Challenges of Real-World Reinforcement Learning","year":"2019","author":"dulac-arnold","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2019.8700455"}],"event":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","start":{"date-parts":[[2020,2,19]]},"location":"Fukuoka, Japan","end":{"date-parts":[[2020,2,21]]}},"container-title":["2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9046688\/9064864\/09065237.pdf?arnumber=9065237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:15:46Z","timestamp":1656360946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9065237\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icaiic48513.2020.9065237","relation":{},"subject":[],"published":{"date-parts":[[2020,2]]}}}