Recurrent networks, hidden states and beliefs in partially observable environments G Lambrechts, A Bolland, D Ernst Transactions on Machine Learning Research, 2022 | 7 | 2022 |
Informed POMDP: Leveraging Additional Information in Model-Based RL G Lambrechts, A Bolland, D Ernst ICML Workshop on New Frontiers in Learning, Control, and Dynamical Systems, 2023 | 5 | 2023 |
Warming up recurrent neural networks to maximise reachable multistability greatly improves learning G Lambrechts, F De Geeter, N Vecoven, D Ernst, G Drion Neural Networks 166, 645-669, 2023 | 3 | 2023 |
Behind the Myth of Exploration in Policy Gradients A Bolland, G Lambrechts, D Ernst arXiv preprint arXiv:2402.00162, 2024 | | 2024 |
Learning to Remember the Past by Learning to Predict the Future G Lambrechts VUB Reinforcement Learning Talks, 2023 | | 2023 |
Belief states of POMDPs and internal states of recurrent RL agents: an empirical analysis of their mutual information G Lambrechts, A Bolland, D Ernst European Workshop on Reinforcement Learning, 2022 | | 2022 |