Timezone: »
It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning combined with behavioural priors informed by actual human-computer interactions. We achieve state-of-the-art and human-level mean performance across all tasks within the MiniWob++ benchmark, a challenging suite of computer control problems, and find strong evidence of cross-task transfer. These results demonstrate the usefulness of a unified human-agent interface when training machines to use computers. Altogether our results suggest a formula for achieving competency beyond MiniWob++ and towards controlling computers, in general, as a human would.
Author Information
Peter Humphreys (Deepmind)
David Raposo (DeepMind)
Tobias Pohlen (DeepMind)
Gregory Thornton (Deepmind)
Rachita Chhaparia (Deepmind)
Alistair Muldal (DeepMind)
Josh Abramson (DeepMind)
Petko Georgiev (Deepmind)
Adam Santoro (DeepMind)
Timothy Lillicrap (Google DeepMind)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: A data-driven approach for learning to control computers »
Wed. Jul 20th 03:35 -- 03:40 PM Room Room 307
More from the Same Authors
-
2022 Poster: Tell me why! Explanations support learning relational and causal structure »
Andrew Lampinen · Nicholas Roy · Ishita Dasgupta · Stephanie Chan · Allison Tam · James McClelland · Chen Yan · Adam Santoro · Neil Rabinowitz · Jane Wang · Feilx Hill -
2022 Poster: Retrieval-Augmented Reinforcement Learning »
Anirudh Goyal · Abe Friesen Friesen · Andrea Banino · Theophane Weber · Nan Rosemary Ke · Adrià Puigdomenech Badia · Arthur Guez · Mehdi Mirza · Peter Humphreys · Ksenia Konyushkova · Michal Valko · Simon Osindero · Timothy Lillicrap · Nicolas Heess · Charles Blundell -
2022 Spotlight: Retrieval-Augmented Reinforcement Learning »
Anirudh Goyal · Abe Friesen Friesen · Andrea Banino · Theophane Weber · Nan Rosemary Ke · Adrià Puigdomenech Badia · Arthur Guez · Mehdi Mirza · Peter Humphreys · Ksenia Konyushkova · Michal Valko · Simon Osindero · Timothy Lillicrap · Nicolas Heess · Charles Blundell -
2022 Spotlight: Tell me why! Explanations support learning relational and causal structure »
Andrew Lampinen · Nicholas Roy · Ishita Dasgupta · Stephanie Chan · Allison Tam · James McClelland · Chen Yan · Adam Santoro · Neil Rabinowitz · Jane Wang · Feilx Hill -
2020 Poster: Probing Emergent Semantics in Predictive Agents via Question Answering »
Abhishek Das · Federico Carnevale · Hamza Merzic · Laura Rimell · Rosalia Schneider · Josh Abramson · Alden Hung · Arun Ahuja · Stephen Clark · Greg Wayne · Feilx Hill -
2019 Poster: Learning Latent Dynamics for Planning from Pixels »
Danijar Hafner · Timothy Lillicrap · Ian Fischer · Ruben Villegas · David Ha · Honglak Lee · James Davidson -
2019 Poster: Meta-Learning Neural Bloom Filters »
Jack Rae · Sergey Bartunov · Timothy Lillicrap -
2019 Oral: Meta-Learning Neural Bloom Filters »
Jack Rae · Sergey Bartunov · Timothy Lillicrap -
2019 Oral: Learning Latent Dynamics for Planning from Pixels »
Danijar Hafner · Timothy Lillicrap · Ian Fischer · Ruben Villegas · David Ha · Honglak Lee · James Davidson -
2019 Poster: Deep Compressed Sensing »
Yan Wu · Mihaela Rosca · Timothy Lillicrap -
2019 Oral: Deep Compressed Sensing »
Yan Wu · Mihaela Rosca · Timothy Lillicrap -
2019 Poster: Composing Entropic Policies using Divergence Correction »
Jonathan Hunt · Andre Barreto · Timothy Lillicrap · Nicolas Heess -
2019 Poster: An Investigation of Model-Free Planning »
Arthur Guez · Mehdi Mirza · Karol Gregor · Rishabh Kabra · Sebastien Racaniere · Theophane Weber · David Raposo · Adam Santoro · Laurent Orseau · Tom Eccles · Greg Wayne · David Silver · Timothy Lillicrap -
2019 Oral: An Investigation of Model-Free Planning »
Arthur Guez · Mehdi Mirza · Karol Gregor · Rishabh Kabra · Sebastien Racaniere · Theophane Weber · David Raposo · Adam Santoro · Laurent Orseau · Tom Eccles · Greg Wayne · David Silver · Timothy Lillicrap -
2019 Oral: Composing Entropic Policies using Divergence Correction »
Jonathan Hunt · Andre Barreto · Timothy Lillicrap · Nicolas Heess -
2018 Poster: Measuring abstract reasoning in neural networks »
Adam Santoro · Feilx Hill · David GT Barrett · Ari S Morcos · Timothy Lillicrap -
2018 Oral: Measuring abstract reasoning in neural networks »
Adam Santoro · Feilx Hill · David GT Barrett · Ari S Morcos · Timothy Lillicrap -
2018 Poster: Fast Parametric Learning with Activation Memorization »
Jack Rae · Chris Dyer · Peter Dayan · Timothy Lillicrap -
2018 Oral: Fast Parametric Learning with Activation Memorization »
Jack Rae · Chris Dyer · Peter Dayan · Timothy Lillicrap -
2017 Poster: Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study »
Samuel Ritter · David GT Barrett · Adam Santoro · Matthew Botvinick -
2017 Poster: Learning to Learn without Gradient Descent by Gradient Descent »
Yutian Chen · Matthew Hoffman · Sergio Gómez Colmenarejo · Misha Denil · Timothy Lillicrap · Matthew Botvinick · Nando de Freitas -
2017 Talk: Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study »
Samuel Ritter · David GT Barrett · Adam Santoro · Matthew Botvinick -
2017 Talk: Learning to Learn without Gradient Descent by Gradient Descent »
Yutian Chen · Matthew Hoffman · Sergio Gómez Colmenarejo · Misha Denil · Timothy Lillicrap · Matthew Botvinick · Nando de Freitas