`

Timezone: »

 
Oral
Imagination-Augmented Agents for Deep Reinforcement Learning
Sébastien Racanière · Theophane Weber · David Reichert · Lars Buesing · Arthur Guez · Danilo Jimenez Rezende · Adrià Puigdomènech Badia · Oriol Vinyals · Nicolas Heess · Yujia Li · Razvan Pascanu · Peter Battaglia · Demis Hassabis · David Silver · Daan Wierstra

Wed Dec 06 03:05 PM -- 03:20 PM (PST) @ Hall A
in Reinforcement Learning, Deep Learning »

We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to interpret predictions from a trained environment model to construct implicit plans in arbitrary ways, by using the predictions as additional context in deep policy networks. I2As show improved data efficiency, performance, and robustness to model misspecification compared to several strong baselines.

Author Information

Seb Racanière (Google DeepMind)

Sébastien Racanière is a Staff Research Engineer in DeepMind. His current interests in ML revolve around the interaction between Physics and Machine Learning, with an emphasis on the use of symmetries. He got his PhD in pure mathematics from the Université Louis Pasteur, Strasbourg, in 2002, with co-supervisors Michèle Audin (Strasbourg) and Frances Kirwan (Oxford). This was followed by a two years Marie-Curie Individual Fellowship in Imperial College, London, and another postdoc in Cambridge (UK). His first job in the industry was at the Samsung European Research Institute, investigating the use of Learning Algorithms in mobile phones, followed by UGS, a Cambridge based company, working on a 3D search engine. He afterwards worked for Maxeler, in London, programming FPGAs. He then moved to Google, and finally DeepMind.

Theophane Weber (DeepMind)
David Reichert (DeepMind)
Lars Buesing (DeepMind)
Arthur Guez (Google)
Danilo Jimenez Rezende (Google DeepMind)
Adrià Puigdomènech Badia (Google DeepMind)
Oriol Vinyals (Google DeepMind)

Oriol Vinyals is a Research Scientist at Google. He works in deep learning with the Google Brain team. Oriol holds a Ph.D. in EECS from University of California, Berkeley, and a Masters degree from University of California, San Diego. He is a recipient of the 2011 Microsoft Research PhD Fellowship. He was an early adopter of the new deep learning wave at Berkeley, and in his thesis he focused on non-convex optimization and recurrent neural networks. At Google Brain he continues working on his areas of interest, which include artificial intelligence, with particular emphasis on machine learning, language, and vision.

Nicolas Heess (Google DeepMind)
Yujia Li (DeepMind)
Razvan Pascanu (Google DeepMind)
Peter Battaglia (DeepMind)
Demis Hassabis (DeepMind)
David Silver (DeepMind)
Daan Wierstra (DeepMind Technologies)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors