Introduction
As a special session of the International Symposium on Artificial Intelligence and Mathematics (ISAIM 2024, Fort Lauderdale, FL, January 8–10, 2024), we are hosting the "Deep Reinforcement Learning: Bridging Theory and Practice" workshop, which lasts two days.
Objective: To foster an understanding and appreciation of the latest advancements in deep reinforcement learning (DRL) by emphasizing the connection between theoretical foundations and practical implementations, and to address the existing challenges facing the field. Rationale: Deep Reinforcement Learning (DRL) is at the forefront of AI research, driving advancements in areas from robotics to finance. While the potential of DRL is vast, there are inherent challenges that need to be addressed, both in theory and in practice. This workshop aims to provide participants with a comprehensive understanding of these challenges, backed by hands-on experiences and in-depth discussions.
Duration: 2 days
Speakers
TBD (photos)
Posters
submit at https://forms.gle/MJuSJHJpuJ3mFevf6
Key Features of the Workshop:
- Expert Speakers: Renowned experts from both academia and industry will share their insights on the latest research, trends, and breakthroughs in DRL.
- Hands-on Labs: Participants will engage in practical sessions that allow them to implement state-of-the-art DRL algorithms, experiencing first-hand the challenges and nuances of real-world applications.
- Discussion Panels: Engage in thought-provoking discussions on the challenges faced in DRL. These will be moderated by leading figures in the DRL community.
- Poster Sessions: Meet your new collaborators and friends!
- Challenges to be Addressed:
- Sample Efficiency: DRL algorithms often require vast amounts of data to train. We'll explore strategies to make them more data-efficient.
- Exploration vs. Exploitation: Balancing the need to explore the environment and exploit known strategies remains a key challenge. We'll delve into techniques that optimize this balance.
- Transfer Learning: How can we leverage knowledge from one domain to enhance performance in another? This session will focus on the current state and challenges of transfer learning in DRL.
- Stability and Convergence: With deep neural networks at their core, DRL algorithms can be prone to instability. We'll discuss strategies to ensure stable learning and convergence.
- Real-world Application Barriers: Deploying DRL in real-world scenarios poses its own set of challenges, from safety concerns to integration issues.
Our workshop will provide insights into navigating these challenges effectively.
Target Audience: Researchers, AI practitioners, graduate students, and industry professionals interested in the cutting-edge developments of Deep Reinforcement Learning and its challenges.