Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optim. | Félix Chalumeau скачать в хорошем качестве

Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optim. | Félix Chalumeau

ICARL Seminar Series - 2024 Winter MEMENTO: Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optimization. Seminar by Félix Chalumeau —————————————————— Abstract: Combinatorial Optimization is crucial to numerous real-world applications, yet still presents challenges due to its (NP-)hard nature. Amongst existing approaches, heuristics often offer the best trade-off between quality and scalability, making them suitable for industrial use. While Reinforcement Learning (RL) offers a flexible framework for designing heuristics, its adoption over handcrafted heuristics remains incomplete within industrial solvers. Existing learned methods still lack the ability to adapt to specific instances, failing to fully utilise newly available information within the constraints of the budget. In response, we present MEMENTO, an RL approach that leverages memory to improve the adaptation of neural solvers at inference time. —————————————————— About the Speaker: Felix Chalumeau is a Research Engineer at InstaDeep, where he works on reinforcement learning for combinatorial optimisation, with a focus on diversity and population-based approaches. He has also worked on other diversity-related topics, including neuroevolution, quality diversity, skill discovery and collaborative skills for multi-agent learning, with publications in international ML conferences, including Neurips and ICLR. Prior to InstaDeep, he studied at Imperial College London and Ecole polytechnique. —————————————————— Links Félix Chalumeau Twitter: x.com/ChalumeauFelix ICARL Site: icarl.doc.ic.ac.uk Twitter: x.com/ic_arl YouTube: @ICARLSeminars ——————————————————