Balanced Q-learning: combining the influence of optimistic and pessimistic targets
From MaRDI portal
Publication:6067050
DOI10.1016/j.artint.2023.104021arXiv2111.02787MaRDI QIDQ6067050
Sunil Kumar Gupta, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh, Majid Abdolshah, Hung Le, Truyen Tran
Publication date: 14 December 2023
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2111.02787
reinforcement learning; \(Q\)-learning target; maximization bias; optimistic updates; pessimistic updates
68T05: Learning and adaptive systems in artificial intelligence
Cites Work