Zobrazeno 1 - 10
of 28
pro vyhledávání: '"van der Pol, Elise"'
Autor:
Biza, Ondrej, Thompson, Skye, Pagidi, Kishore Reddy, Kumar, Abhinav, van der Pol, Elise, Walters, Robin, Kipf, Thomas, van de Meent, Jan-Willem, Wong, Lawson L. S., Platt, Robert
Imitation learning of robot policies from few demonstrations is crucial in open-ended applications. We propose a new method, Interaction Warping, for learning SE(3) robotic manipulation policies from a single demonstration. We infer the 3D mesh of ea
Externí odkaz:
http://arxiv.org/abs/2306.12392
Autor:
Muglich, Darius, de Witt, Christian Schroeder, van der Pol, Elise, Whiteson, Shimon, Foerster, Jakob
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, when agents arbitrarily converge on one out of many equivalent but mutual
Externí odkaz:
http://arxiv.org/abs/2210.12124
Large graphs commonly appear in social networks, knowledge graphs, recommender systems, life sciences, and decision making problems. Summarizing large graphs by their high level properties is helpful in solving problems in these settings. In spectral
Externí odkaz:
http://arxiv.org/abs/2207.14589
Autor:
Kasarla, Tejaswi, Burghouts, Gertjan J., van Spengler, Max, van der Pol, Elise, Cucchiara, Rita, Mettes, Pascal
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 equipped with this inductive bias and therefore many alternative solu
Externí odkaz:
http://arxiv.org/abs/2206.08704
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 between global symmetries in the joint state-action space of cooperative m
Externí odkaz:
http://arxiv.org/abs/2110.04495
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) Equivariant Graph Neural Networks (SEGNNs) that generalise equivariant graph net
Externí odkaz:
http://arxiv.org/abs/2110.02905
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 three cases where small changes in how we sample negative states in th
Externí odkaz:
http://arxiv.org/abs/2107.11676
This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep reinforcement lea
Externí odkaz:
http://arxiv.org/abs/2006.16908
This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, while the map and transition f
Externí odkaz:
http://arxiv.org/abs/2002.11963
A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we in
Externí odkaz:
http://arxiv.org/abs/1911.12247