BibTeX

@article{2403,
  author =		 "Vincent, T. and  Palenicek, D. and  Belousov, B. and  Peters, J. and  D'Eramo, C.",
  year =		 "2025",
  title =		 "Iterated Q-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning",
  booktitle =		 "Transactions on Machine Learning Research (TMLR)",
  key =			 "deep reinforcement learning, temporal difference, approximate value iteration",
  URL =			 "https://arxiv.org/pdf/2403.02107",
  crossref =		 "p11833"
}