Synthetic Intelligence Forum is excited to convene a session about "Sequential Decision Analytics" with Warren Powell, PhD (Professor Emeritus of Operations Research and Financial Engineering, Princeton University).

Topic: Many real world scenarios involving sequential decision making require successive decisions to be made under conditions of uncertainty. After a decision is a made some new information arrives in a variety of forms which is then used to update what we understand about the system. This sequencing implies that we need to make decisions before the new information has arrived, which means we have to optimize to find the best decision under uncertainty.

In this talk, Professor Powell shares his perspectives about concepts and applications of sequential decision analytics. He asserts that problems related to sequential decision-making are studied in at least fifteen distinct fields, using eight different notational systems and a host of solution approaches. He refers to this as the “jungle of stochastic optimization.” Each of these books, and their associated communities, can be described as a method, or set of methods, and the problems for which these methods work. Sequential decision analytics turns this around because it is a field centered on the broad problem class of sequential decision problems, drawing on a broad class of methods that span every solution approach that might be used.

Biography: Warren Powell is a Professor Emeritus after retiring from Princeton where he served as a faculty member in the Department of Operations Research and Financial Engineering at Princeton University where he has taught since 1981.

In 1990, he founded CASTLE Laboratory which spans research in computational stochastic optimization with applications initially in transportation and logistics. In 2011, he founded the Princeton laboratory for ENergy Systems Analysis (PENSA) to tackle the rich array of problems in energy systems analysis. In 2013, this morphed into “CASTLE Labs,” focusing on computational stochastic optimization and learning.

He is the author of Reinforcement Learning and Stochastic Optimization: A unified framework for sequential decisions, Approximate Dynamic Programming: Solving the curses of dimensionality and co-author (with Ilya Ryzhov) of Optimal Learning (both published by Wiley). Co-editor (with J. Si, A. Barto, and D. Wunsch) Learning and Approximate Dynamic Programming: Scaling up to the Real World.

Profiles of the host and presenter:
• Vik Pant, PhD -   / vikpant  
• Warren Powell, PhD -   / warrenbpowell  

Web profiles of Warren Powell, PhD:
• Computational Stochastic Optimization and Learning at Princeton University - https://castlelab.princeton.edu/biogr...
• Optimal Dynamics - https://www.optimaldynamics.com/about

Join Synthetic Intelligence Forum online:
• Website - http://www.synthint.org
• LinkedIn (Page) -   / synthint  
• LinkedIn (Group) -   / 12092618  
• YouTube -    / syntheticintelligenceforum  

Special Thanks to our Partner:
• ET Business Services