activity
20092019
most citedImproved Adversarial Systems for 3D Object Generation and Reconstruction

64 citations · 109 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2019

Human Motion Prediction via Pattern Completion in Latent Representation Space

Yi Tian Xu, Yaqiao Li, David Meger

Inspired by ideas in cognitive science, we propose a novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space.…

cs.LG201714 cited

Bayesian Policy Gradients via Alpha Divergence Dropout Inference

Peter Henderson, Thang Doan, Riashat Islam +1

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We pr…

cs.LG2017

OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning

Peter Henderson, Wei-Di Chang, Pierre-Luc Bacon +3

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for…

cs.AI201717 cited

Benchmark Environments for Multitask Learning in Continuous Domains

Peter Henderson, Wei-Di Chang, Florian Shkurti +3

As demand drives systems to generalize to various domains and problems, the study of multitask, transfer and lifelong learning has become an increasingly important pursuit. In disc…

cs.CV201764 cited

Improved Adversarial Systems for 3D Object Generation and Reconstruction

Edward Smith, David Meger

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects. While GANs have been used in this domain prev…

cs.CV200914 cited

Semantic Robot Vision Challenge: Current State and Future Directions

Scott Helmer, David Meger, Pooja Viswanathan +9

The Semantic Robot Vision Competition provided an excellent opportunity for our research lab to integrate our many ideas under one umbrella, inspiring both collaboration and new re…