Objective Mismatch in Model-based Reinforcement Learning

2 code implementations • ICLR 2020 • Nathan Lambert, Brandon Amos, Omry Yadan, Roberto Calandra

In our experiments, we study this objective mismatch issue and demonstrate that the likelihood of one-step ahead predictions is not always correlated with control performance.

Model-based Reinforcement Learning reinforcement-learning +1

Multi-GPU Training of ConvNets

no code implementations • 20 Dec 2013 • Omry Yadan, Keith Adams, Yaniv Taigman, Marc'Aurelio Ranzato

In this work we evaluate different approaches to parallelize computation of convolutional neural networks across several GPUs.