Janarthanan Rajendran

Janarthanan Rajendran is an Assistant Professor and the Sexton Chair in Reinforcement Learning at the Faculty of Computer Science, Dalhousie University, in Halifax, Nova Scotia, Canada. He is actively involved in research, teaching, and mentoring, with a focus on deep reinforcement learning and its applications in complex, dynamic environments.

Education:

• Postdoctoral Fellow, Mila Quebec AI Institute and University of Montreal, Canada (2023)
• PhD in Computer Science and Engineering (AI stream), University of Michigan, Ann Arbor, USA (2021)
• MTech and BTech in Electrical Engineering, Indian Institute of Technology Madras, India (2016)

His research focuses on enabling machines to learn through interaction, with core interests in deep reinforcement learning, model-based RL, multi-agent systems, transfer learning, and applications in materials science and economics. He also explores the integration of large language models and foundation models into reinforcement learning frameworks. His work emphasizes adaptivity, lifelong learning, and societal implications of AI.

The most recent publications show a strong trend in advancing cooperative multi-agent systems, developing adaptive and memory-efficient RL methods, and applying RL to real-world challenges such as crystal design and dynamic pricing. His research bridges theoretical innovation with practical application, often in interdisciplinary contexts.

Scientific Awards:

• Sexton Chair in Reinforcement Learning

Dr. Rajendran is actively involved in mentoring graduate students and fostering an inclusive research environment. He is currently recruiting PhD and MCS students at Dalhousie University. He has no formal grants listed in the text, but his research chair and active publication record suggest strong funding support. He is also engaged in the broader AI community, having organized and participated in major conferences such as the Atlantic Canada AI Summit and NeurIPS.

Labs and Research Groups: He leads a research group focused on deep reinforcement learning at Dalhousie University, working on topics including model-based RL, off-policy learning, and leveraging external knowledge sources. The group emphasizes inclusivity and supports underrepresented groups in computer science research.