Colloquium Archives for Academic Year 2021


Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning.

When: Wed, October 21, 2020 - 1:30pm
Where: https://umd.zoom.us/j/2920984437
Speaker: Jayesh Gupta (Stanford and Microsoft Research) - https://www.cs.umd.edu/talks/rlss
Abstract: Multi-agent reinforcement learning (MARL) requires coordination to efficiently solve certain tasks. Fully centralized control is often infeasible in such domains due to the size of joint action spaces. Coordination graph based formalization allows reasoning about the joint action based on the structure of interactions. However, they often require domain expertise in their design. In this talk, we will discuss the recently introduced deep implicit coordination graph (DICG) architecture for such scenarios. DICG consists of a module for inferring the dynamic coordination graph structure which is then used by a graph neural network based module to learn to implicitly reason about the joint actions or values. DICG allows learning the tradeoff between full centralization and decentralization via standard actor-critic methods to significantly improve coordination for domains with large numbers of agents. https://arxiv.org/abs/2006.11438

Gap problems in higher dimensions: from Kronecker sequences to quantum oscillators

When: Wed, November 11, 2020 - 3:15pm
Where: Recording: https://umd.zoom.us/rec/share/M7w0c-iDrTSrWcvYPZOxo5a82H8JqO1qrGOwBBv7X5spF9AtWS1dclLMUVX21vCg.aDiPqpEl59sAn2XM?startTime=1605125878000
Speaker: Jens Marklof (University of Bristol) - https://people.maths.bris.ac.uk/~majm/


Abstract: Take a point on the unit circle and rotate it N times by a
fixed angle. The N points thus generated partition the circle into N
intervals. A beautiful fact, first conjectured by Hugo Steinhaus in
the 1950s and proved independently by Vera Sos, Janos Suranyi and
Stanislaw Swierczkowski, is that for any choice of N, no matter how
large, these intervals can have at most three distinct lengths. In
this lecture I will explore an interpretation of the three gap theorem
in terms of the space of Euclidean lattices, which will produce
various new results in higher dimensions, including nearest neighbour
distances in multi-dimensional Kronecker sequences, free flights in
the Lorentz gas, and quantum spectra of harmonic oscillators. The
lecture is based on joint work with Alan Haynes (Houston) and Andreas
Strombergsson (Uppsala). Recording

Wikipedia, https://en.wikipedia.org/wiki/Three-gap_theorem
J. Marklof and A. Strombergsson, The three gap theorem and the space
of lattices, American Mathematical Monthly 124 (2017) 741-745
https://people.maths.bris.ac.uk/~majm/bib/threegap.pdf
A. Haynes and J. Marklof, Higher dimensional Steinhaus and Slater
problems via homogeneous dynamics, Annales scientifiques de l'Ecole
normale superieure 53 (2020) 537-557
https://people.maths.bris.ac.uk/~majm/bib/steinhaus.pdf
A. Haynes and J. Marklof, A five distance theorem for Kronecker
sequences, preprint arXiv:2009.08444
https://people.maths.bris.ac.uk/~majm/bib/steinhaus2.pdf

(Join Zoom Meetinghttps://umd.zoom.us/j/7752961556?pwd=eEw2T2RSU2RwQTJiUWlmc0dVbDBUdz09

Meeting ID: 775 296 1556
Passcode: Bristol)

A Closer Look at Deep Policy Gradient Algorithms

When: Wed, November 18, 2020 - 1:00pm
Where: https://umd.zoom.us/j/2920984437
Speaker: Logan Engstrom (Massachusetts Institute of Technology) -
Abstract: Deep reinforcement learning methods are behind some of the most publicized recent results in machine learning. In spite of these successes, however, deep RL methods face a number of systemic issues: brittleness to small changes in hyperparameters, high reward variance across runs, and sensitivity to seemingly small algorithmic changes. In this talk we take a closer look at the potential root of these issues. Specifically, we study how the policy gradient primitives underlying popular deep RL algorithms reflect the principles informing their development.

Multi-Agent Reinforcement Learning: Systems for Evaluation

When: Wed, January 6, 2021 - 1:00pm
Where: https://umd.zoom.us/j/2920984437
Speaker: Justin Terry (University of Maryland) -
Abstract: Multi-Agent Reinforcement Learning: Systems for Evaluation

This talk discusses 4 papers and an ongoing project that deal with various aspects of designing software systems for multi-agent reinforcement learning, that allow for more productive and reproducible research, a democratization of research multi-agent reinforcement learning to university level researchers, and a new problems that are challenging to reinforcement learning in important ways. All works are centered around the PettingZoo project. This talk is specifically tailored to a very broad audience.

Papers:

https://arxiv.org/abs/2009.14471
https://arxiv.org/abs/2009.13051
https://arxiv.org/abs/2009.09341
https://arxiv.org/abs/2008.08932

AWM Distinguished Colloquium

When: Wed, February 17, 2021 - 3:15pm
Where: Online
Speaker: Gigliola Staffilani (MIT) - http://math.mit.edu/~gigliola/
Abstract: TBA

TBA (AWM Distinguished Colloquium)

When: Wed, March 24, 2021 - 3:00pm
Where: Online
Speaker: Sommer Gentry (USNA) - https://www.usna.edu/Users/math/gentry/index.php