When: Thursday, June 17, 2021, 12pm (CEST).

Where: Zoom online, check the address in the Google Calendar Event.

Topic: Tractable Novelty Exploration over Continuous and Discrete Sequential Decision Problems.

Speaker: Nir Lipovetzky, Senior Lecturer in Artificial Intelligence at the University of Melbourne.

Abstract

Sequential decision problems, where an agent is trying to find a sequence of actions to maximise a utility function or to satisfy a goal condition, have been the focus of different research communities. This talk focuses on the latest advances over width-based planning algorithms, which have shown to yield state-of-the-art AI Planners that rely mostly on structural exploration features, rather than goal-oriented heuristics.

Width-based planners search for a solution using a measure of the novelty of states, where states need to be defined over a set of features. It is known that state novelty evaluation is exponential on the cardinality of the set of features. In this talk, I will address two limitations of current width-based planning: 1) How to define state features over continuous dynamics, where the space of features is unbounded, and 2) present new methods to obtain approximations of novelty linear in the cardinality of the set of features instead of exponential.

I will discuss the performance of the resulting polynomial planners over discrete sequential decision problems ( classical planning) and compare over continuous problems with PPO, a state-of-the-art DRL algorithm. The continuous problems are “classical control” benchmarks from openAI gym.

Short Bio

Nir Lipovetzky is a Senior Lecturer in Artificial Intelligence at the School of Computing and Information Systems, The University of Melbourne. He’s a member of the Agent Lab group. He completed his PhD at the Artificial Intelligence and Machine Learning Group, Universitat Pompeu Fabra, under the supervision of Prof. Hector Geffner. Then, he was a research fellow for 3 years under the supervision of Prof. Peter Stuckey and Prof. Adrian Pearce, working on solving Mining Scheduling problems through automated planning, constraint programming and operations research techniques.

His research focuses on how to introduce different approaches to the problem of inference in sequential decision problems, as well as applications to autonomous systems.

Material

  • Video (Passcode 7e5@pNu^)