Successor Clusters : A Behavior Basis for Unsupervised Zero-Shot Reinforcement Learning
Source
Transactions on Machine Learning Research - ISSN 2835-8856-07 (2025) p. 1-33
GPI-tree search : algorithms for decision-time planning with the general policy improvement theorem
Source
Neural computing and applications - ISSN 0941-0643-37:23 (2025) p. 18989-19007
GPI-tree search : algorithms for decision-time planning with the general policy improvement theorem
Source
Adaptive and Learning Agents Workshop (ALA), collocated with AAMAS, 29-30 May, 2023, London, UK- () p. 1-8
A case for feature-based successor features for transfer in reinforcement learning
Source
34th Benelux Conference on Artificial Intelligence and the 31 Belgium Dutch Conference on Machine Learning (BNAIC/BENELEARN 2022), 7-9 November, 2022, Mechelen, Belgium- () p. 1-16
Deep learning of intrinsically motivated options in the arcade learning environment
Source
Deep Reinforcement Learning Workshop, NeurIPS 2022, 9 December, 2022- () p. 1-14