Sergio Gómez Colmenarejo — accepted AI-conference papers

2020

Scaling data-driven robotics with reward sketching and batch reinforcement learning

Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushova, Scott Reed, Rae Jeong +10

RSS 2020poster

By harnessing a growing dataset of robot experience, we learn control policies for a diverse and increasing set of related manipulation tasks. To make this possible, we introduce reward sketching: an effective way of eliciting human preferences to learn the reward function for a new task. This rewar…

Cited by 168 Source ↗PDF ↗code ↗Scholar ↗

2020

Task-Relevant Adversarial Imitation Learning

Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gómez Colmenarejo, David Budden, Serkan Cabi +3

CoRL 2020

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to

Cited by 0 Source ↗PDF ↗Scholar ↗

2018

Learning Awareness Models

Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal +4

ICLR 2018poster

We consider the setting of an agent with a fixed body interacting with an unknown and uncertain external world. We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world. In spite of being trained with only internally ava…

Cited by 58 Source ↗PDF ↗Scholar ↗

2017

Learned Optimizers that Scale and Generalize

Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gómez Colmenarejo, Misha Denil, Nando Freitas +1

ICML 2017poster

Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes…

Cited by 349 Source ↗PDF ↗Scholar ↗

2017

Learning to Learn without Gradient Descent by Gradient Descent

Yutian Chen, Matthew W. Hoffman, Sergio Gómez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Matt Botvinick +1

ICML 2017poster

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gauss…

Cited by 345 Source ↗PDF ↗Scholar ↗

2017

Parallel Multiscale Autoregressive Density Estimation

Scott Reed, Aäron Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Ziyu Wang, Yutian Chen +2

ICML 2017poster

PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In th…

Cited by 261 Source ↗PDF ↗Scholar ↗

2017

The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously

Serkan Cabi, Sergio Gómez Colmenarejo, Matthew W. Hoffman, Misha Denil, Ziyu Wang, Nando Freitas

CoRL 2017

This paper introduces the Intentional Unintentional (IU) agent. This agent endows the deep deterministic policy gradients (DDPG) agent for continuous control with the ability to solve several tasks simultaneously. Learning to solve many tasks simultaneously has been a long-standing, core goal of art

Cited by 0 Source ↗PDF ↗Scholar ↗