A fundamental task for artificial intelligence is learning. Last week, sparse models were discussed in the context of supervised and unsupervised learning. Inspired by human learning, the reinforcement learning paradigm has high potential for autonomous agents, although it suffers from scalability issues [Mocanu et al. AAMAS 2021]. Further on, we introduce dynamic sparse training in deep reinforcement learning [Sokar et al., IJCAI 2022], and pave the ground for scalable deep reinforcement learning.

We describe some very recent progress in the field that could be used to foster the generalization performance of sparsely trained RL agents over their densely trained counterparts [Grooten et al., AAMAS 2023], while at the same time, reducing considerably their computational and memory requirements in both, training and inference.

Elena Mocanu is an Assistant Professor at the University of Twente. She received her PhD in machine learning from the Eindhoven University of Technology in 2017. She visited the Technical University of Denmark (2015), the University of Texas at Austin (2016), and the University of Alberta (2022), working on machine learning and decision-making through the means of sparse neural networks.

 

As a mathematician passionate about neural networks, her current research focuses on understanding sparse neural networks and how their learning capabilities can be improved.

 

 

---

 

 
About the EuroCC-2 project

EuroCC 2 will work to identify and address the skills gaps in the European High Performance Computing (HPC) ecosystem and coordinate cooperation across Europe to ensure a consistent skills base.

The role of EuroCC 2 is to establish and run a network of more than 30 NCCs across the EuroHPC Participating States. The NCCs act as single points of access in each country between stakeholders and national and EuroHPC systems. They operate on a regional and national level to liaise with local communities, in particular SMEs, map HPC competencies and facilitate access to European HPC resources for users from the private and public sector.

EuroCC 2 delivers training, interacts with industry, develops competence mapping and communication materials and activities, and supports the adoption of HPC services in other related fields, such as quantum computing, artificial intelligence (AI), high performance data analytics (HPDA) to expand the HPC user base.

 

---

 

This project has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101101903. The JU receives support from the European Union’s programme Digital Europe and Germany, Bulgaria, Austria, Croatia, Cyprus, Czech Republic, Denmark, Estonia, Finland, Greece, Hungary, Ireland, Italy, Lithuania, Latvia, Poland, Portugal, Romania, Slovenia, Spain, Sweden, France, Netherlands, Belgium, Luxembourg , Slovakia, Norway, Switzerland, Turkey, the Republic of North Macedonia, Iceland, Montenegro and Serbia. 

 

---