From probabilistic bisimulation to representation learning via metrics

From probabilistic bisimulation to representation learning via metrics

From Strachey Lectures by Oxford University

December 2, 2024 · 55 min

About this episode

Professor Prakash Panangaden discusses the evolution of bisimulation concepts and their applications in machine learning.

Strachey Lecture: From probabilistic bisimulation to representation learning via metrics - Professor Prakash Panangaden Bisimulation is a fundamental equivalence relation in process theory invented by Robin Milner and with an elegant fixed-point definition due to David Park. In this talk I will review the concept of bisimulation and then discuss its probabilistic analogue. This was extended to systems with continuous state spaces. Despite its origin in theoretical work, it has proved to be useful in fields like machine learning, especially reinforcement learning. Surprisingly, it turned out that one could prove a striking theorem: a theorem that pins down exactly what differences one can "see" in process behaviours when two systems are not bisimilar. However, it is questionable whether a concept like equivalence is the right one for quantitative systems. If two systems are almost, but not quite, the same, bisimulation would just say that they are not equivalent. One would like to say in some way that they are "almost" the same. Metric analogues of bisimulation were developed to capture a notion of behavioral similarity rather than outright equivalence. These ideas have been…

People in this episode

Host: Oxford University

Guest: Professor Prakash Panangaden

Topics covered

  • bisimulation
  • probabilistic systems
  • representation learning
  • machine learning
  • reinforcement learning
  • behavioral similarity

Keywords

  • bisimulation
  • probabilistic bisimulation
  • representation learning
  • Markov decision processes
  • machine learning
  • theoretical work

More episodes of Strachey Lectures

Explore listener stats, chart rankings, contacts and more on the Strachey Lectures podcast page.