{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:30:00Z","timestamp":1768519800962,"version":"3.49.0"},"reference-count":8,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"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":[[2025,7,15]]},"DOI":"10.1109\/codit66093.2025.11321834","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:48Z","timestamp":1768423008000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Model-Free Reinforcement Learning Algorithms for Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Ngoc Quoc Huy","family":"Hoang","sequence":"first","affiliation":[{"name":"Deggendorf Institute of Technology, Technology Campus Cham,Cham,Germany,93413"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasaman","family":"Mohammadidargah","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Technology Campus Cham,Cham,Germany,93413"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitrii","family":"Dobriborsci","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Technology Campus Cham,Cham,Germany,93413"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref4","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","author":"Haarnoja"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint arXiv:1509.02971"},{"key":"ref6","article-title":"Hindsight experience replay","volume":"30","author":"Andrychowicz","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref8","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","author":"Raffin","year":"2021"}],"event":{"name":"2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)","location":"Split, Croatia","start":{"date-parts":[[2025,7,15]]},"end":{"date-parts":[[2025,7,18]]}},"container-title":["2025 11th International Conference on Control, Decision and Information Technologies (CoDIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11321217\/11321218\/11321834.pdf?arnumber=11321834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:56:39Z","timestamp":1768463799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11321834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":8,"URL":"https:\/\/doi.org\/10.1109\/codit66093.2025.11321834","relation":{},"subject":[],"published":{"date-parts":[[2025,7,15]]}}}