Back
  1. Home
  2. Profile of Gaspard Lambrechts (ULiège)

Lambrechts Gaspard

Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids

Montefiore Institute

See author's contact details
Main Referenced Co-authors
Ernst, Damien  (12)
Bolland, Adrien  (5)
Louppe, Gilles  (3)
Close, Pierre  (2)
De Geeter, Florent  (2)
Main Referenced Keywords
Reinforcement Learning (6); Asymmetric Learning (4); POMDP (4); reinforcement learning (4); RL (4);
Main Referenced Unit & Research Centers
Montefiore Institute - Montefiore Institute of Electrical Engineering and Computer Science - ULiège (2)
GIGA In silico medecine-Biomechanics Research Unit - ULiège (1)
Main Referenced Disciplines
Computer science (18)
Biochemistry, biophysics & molecular biology (2)
Physical, chemical, mathematical & earth Sciences: Multidisciplinary, general & others (2)
Personal website

Publications (total 18)

The most downloaded
826 downloads
Lambrechts, G. (2025). Reinforcement Learning in Partially Observable Markov Decision Processes: Learning to Remember the Past by Learning to Predict the Future [Doctoral thesis, ULiège - University of Liège]. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/328700 https://hdl.handle.net/2268/328700

The most cited

6 citations (Scopus®)

Lambrechts, G., Bolland, A., & Ernst, D. (2022). Recurrent networks, hidden states and beliefs in partially observable environments. Transactions on Machine Learning Research. https://hdl.handle.net/2268/293614

The most significant

Lambrechts, G., Ernst, D., & Mahajan, A. (2025). A Theoretical Justification for Asymmetric Actor-Critic Algorithms. Proceedings of Machine Learning Research.
Peer Reviewed verified by ORBi

Lambrechts, G., Bolland, A., & Ernst, D. (2024). Informed POMDP: Leveraging Additional Information in Model-Based RL. Reinforcement Learning Journal.
Peer reviewed

Lambrechts, G.* , Claes, Y.* , Geurts, P., & Ernst, D. (July 2024). Parallelizing Autoregressive Generation with Variational State Space Models [Paper presentation]. ICML Workshop on Next Generation of Sequence Modeling Architectures, Vienne, Austria.
Peer reviewed
* These authors have contributed equally to this work.

Lambrechts, G.* , De Geeter, F.* , Vecoven, N.* , Ernst, D., & Drion, G. (August 2023). Warming up recurrent neural networks to maximise reachable multistability greatly improves learning. Neural Networks, 166, 645-669. doi:10.1016/j.neunet.2023.07.023
Peer Reviewed verified by ORBi
* These authors have contributed equally to this work.

Lambrechts, G., Bolland, A., & Ernst, D. (2022). Recurrent networks, hidden states and beliefs in partially observable environments. Transactions on Machine Learning Research.
Peer Reviewed verified by ORBi


De Geeter, F., Lambrechts, G., Ernst, D., & Drion, G. (2026). Parallelizable memory recurrent units. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/339817.

Hu, E. S.* , Wang, J.* , Yuan, X.* , Luo, F., Li, M., Lambrechts, G., Rybkin, O., & Jayaraman, D. (2025). Real-World Reinforcement Learning of Active Perception Behaviors. Advances in Neural Information Processing Systems.
Peer Reviewed verified by ORBi
* These authors have contributed equally to this work.

Ebi, D., Lambrechts, G., Ernst, D., & Böhm, K. (17 July 2025). Informed Asymmetric Actor-Critic: Theoretical Insights and Open Questions [Paper presentation]. European Workshop on Reinforcement Learning, Tübingen, Germany.
Peer reviewed

Bolland, A., Lambrechts, G., & Ernst, D. (17 July 2025). Behind the Myth of Exploration in Policy Gradients [Paper presentation]. European Workshop on Reinforcement Learning, Tübingen, Germany.
Peer reviewed

Bolland, A., Lambrechts, G., & Ernst, D. (17 July 2025). Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures [Paper presentation]. European Workshop on Reinforcement Learning, Tübingen, Germany.
Peer reviewed

Lambrechts, G. (2025). Partial Observability and Asymmetric Observability [Paper presentation]. BeNeRL Workshop, Eindhoven, Netherlands.

Lambrechts, G., Ernst, D., & Mahajan, A. (2025). A Theoretical Justification for Asymmetric Actor-Critic Algorithms. Proceedings of Machine Learning Research.
Peer Reviewed verified by ORBi

Lambrechts, G. (2025). Reinforcement Learning in Partially Observable Markov Decision Processes: Learning to Remember the Past by Learning to Predict the Future [Doctoral thesis, ULiège - University of Liège]. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/328700

Pirenne, L., Lambrechts, G., Marlier, N., de la Brassinne Bonardeaux, M., Louppe, G., & Ernst, D. (2025). Contributive Attribution for Question Answering via Tree-based Context Pruning. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/337121.

Lambrechts, G., Bolland, A., & Ernst, D. (2024). Informed POMDP: Leveraging Additional Information in Model-Based RL. Reinforcement Learning Journal.
Peer reviewed

Lambrechts, G.* , Claes, Y.* , Geurts, P., & Ernst, D. (July 2024). Parallelizing Autoregressive Generation with Variational State Space Models [Paper presentation]. ICML Workshop on Next Generation of Sequence Modeling Architectures, Vienne, Austria.
Peer reviewed
* These authors have contributed equally to this work.

Louette, A., Lambrechts, G., Ernst, D., Pirard, E., & Dislaire, G. (2024). Reinforcement learning to improve delta robot throws for sorting scrap metal. ORBi-University of Liège. https://orbi.uliege.be/handle/2268/319923.

Lambrechts, G. (2023). Learning to Remember the Past by Learning to Predict the Future [Paper presentation]. VUB Reinforcement Learning Talks.

Lambrechts, G.* , De Geeter, F.* , Vecoven, N.* , Ernst, D., & Drion, G. (August 2023). Warming up recurrent neural networks to maximise reachable multistability greatly improves learning. Neural Networks, 166, 645-669. doi:10.1016/j.neunet.2023.07.023
Peer Reviewed verified by ORBi
* These authors have contributed equally to this work.

Joiret, M., Leclercq, M., Lambrechts, G., Rapino, F., Close, P., Louppe, G., & Geris, L. (06 April 2023). Cracking the genetic code with neural networks. Frontiers in Artificial Intelligence, 6. doi:10.3389/frai.2023.1128153
Peer Reviewed verified by ORBi

Joiret, M., Leclercq, M., Lambrechts, G., Rapino, F., Close, P., Louppe, G., & Geris, L. (2023). Cracking the genetic code with neural networks (poster) [Paper presentation]. Neural networks: real versus man-made, Liège, Belgium.

Lambrechts, G., Bolland, A., & Ernst, D. (September 2022). Belief states of POMDPs and internal states of recurrent RL agents: an empirical analysis of their mutual information [Paper presentation]. European Workshop on Reinforcement Learning, Milan, Italy.
Peer reviewed

Lambrechts, G., Bolland, A., & Ernst, D. (2022). Recurrent networks, hidden states and beliefs in partially observable environments. Transactions on Machine Learning Research.
Peer Reviewed verified by ORBi

Contact ORBi