log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
PhD Proposal: Multi-Agent Autonomous Decision Making in Artificial Intelligence
Saptarashmi Bandyopadhyay
4107 Brendan Iribe Center for Computer Science and Engineering (IRB)
Friday, May 3, 2024, 3:00-4:45 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract
Abstract:
Multi-Agent Autonomous Decision Making, especially Multi-Agent Reinforcement Learning (MARL), is an emerging area of Artificial Intelligence (AI) where autonomous agents interact with each other, fostering competition and/or cooperation in real world problems like climate change, supply chains, self-driving cars, sports, interdiction games, war games among other uses.

The PhD proposal has been arranged considering the research works already carried out and published and those are continuing in the areas of AI Alignment and Social Cooperation of Autonomous AI Agents, Speedup and Scalability for Efficient Multi-Agent AI, Multi-Agent Explainable AI and Unlearning to Build Trustworthy AI and Real World Applications of Multi-Agent AI for Climate Conservation, Global Supply Chain orchestration etc.
 
Examining Committee

Chair:

Dr. John Dickerson

Department Representative:

Dr. Tom Goldstein

Members:

Dr. Hal Daumé
Bio

Saptarashmi Bandyopadhyay is a 4th year PhD student of Computer Science, advised by Prof. John Dickerson. His PhD research is on Multi-Agent Autonomous Decision Making in AI to develop and deploy autonomous AI agents, focusing on Multi-Agent RL (MARL), Imitation Learning, Meta Learning and other Autonomous Decision Making paradigms with application to climate conservation, autonomous orchestration in supply chains, AI privacy, aligning LLM agents, speeding up multi-agent training with JAX etc. He has been an AI Resident at Google X, a DoGood Fellow, a Dean's Summer Fellow at UMD, Research Intern at CNRS LORIA, INRIA Nancy; German Center of AI (DFKI) Saarbrucken; and the University of Saarland along with working on DoD/IC, NSF, NIH projects.

This talk is organized by Migo Gui