70 citations · 261 across the 14 of their papers we have counts for
10 papers · 1 filter
Equivariant Networks for Zero-Shot Coordination
Darius Muglich, Christian Schroeder de Witt, Elise van der Pol +2
Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, whe…
Maximum Class Separation as Inductive Bias in One Matrix
Tejaswi Kasarla, Gertjan J. Burghouts, Max van Spengler +3
Maximizing the separation between classes constitutes a well-known inductive bias in machine learning and a pillar of many traditional algorithms. By default, deep networks are not…
Multi-Agent MDP Homomorphic Networks
Elise van der Pol, Herke van Hoof, Frans A. Oliehoek +1
This paper introduces Multi-Agent MDP Homomorphic Networks, a class of networks that allows distributed execution using only local information, yet is able to share experience betw…
Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
Johannes Brandstetter, Rob Hesselink, Elise van der Pol +2
Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivarian…
The Impact of Negative Sampling on Contrastive Structured World Models
Ondrej Biza, Elise van der Pol, Thomas Kipf
World models trained by contrastive learning are a compelling alternative to autoencoder-based world models, which learn by reconstructing pixel states. In this paper, we describe…
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
Elise van der Pol, Daniel E. Worrall, Herke van Hoof +2
This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint stat…
Plannable Approximations to MDP Homomorphisms: Equivariance under Actions
Elise van der Pol, Thomas Kipf, Frans A. Oliehoek +1
This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by…
Visual Rationalizations in Deep Reinforcement Learning for Atari Games
Laurens Weitkamp, Elise van der Pol, Zeynep Akata
Due to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games.…
Hyperspherical Prototype Networks
Pascal Mettes, Elise van der Pol, Cees G. M. Snoek
This paper introduces hyperspherical prototype networks, which unify classification and regression with prototypes on hyperspherical output spaces. For classification, a common app…
Beyond Local Nash Equilibria for Adversarial Networks
Frans A. Oliehoek, Rahul Savani, Jose Gallego +2
Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a `local Nash equilibrium` (LNE). Such LNEs,…