Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning

Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 17 December 2025 V1 Latest version Share on Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning Author : Hanxiao CHEN 0000-0001-9603-3656 [email protected] Authors Info & Affiliations https://doi.org/10.22541/au.176599442.26320853/v1 283 views 76 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Humans possess the advanced ability to grab, hold, and manipulate objects with dexterous hands. What about robots? Can they interact with the surrounding world environment intelligently to achieve certain goals (e.g. grasping, button-pushing), even finish complicated tasks like human hands? Actually, robotic manipulation is central to achieving the premise of robotics and represents immense potentials to be widely applied in various practical scenarios like industries and homes. In this work, we aim to address multiple robotic manipulation tasks like grasping, button-pushing, and door-opening with reinforcement learning (RL), state representation learning (SRL), and imitation learning. For diverse missions, we self-built the PyBullet or MuJoCo simulated environments and independently explored three different learning-style methods to successfully solve such tasks: (1) Normal reinforcement learning approaches; (2) Combined state representation learning (SRL) and RL methods; (3) Imitation learning bootstrapped RL algorithms. Supplementary Material File (robotic manipulation_hanxiao.pdf) Download 2.74 MB Information & Authors Information Version history V1 Version 1 17 December 2025 Copyright This work is licensed under a MIT License Keywords imitation learning reinforcement learning representation learning robotic manipulation state representation learning Authors Affiliations Hanxiao CHEN 0000-0001-9603-3656 [email protected] Cambridge Online AI Research Internship View all articles by this author Metrics & Citations Metrics Article Usage 283 views 76 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Hanxiao CHEN. Robotic Manipulation with Reinforcement Learning, State Representation Learning, and Imitation Learning. Authorea . 17 December 2025. DOI: https://doi.org/10.22541/au.176599442.26320853/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176599442.26320853/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fffc9cb5b4e0db4',t:'MTc3OTQ5NDUwOQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();