Search Results for author: Raia Hadsell

Found 41 papers, 20 papers with code

CoMic: Co-Training and Mimicry for Reusable Skills

no code implementations ICML 2020 Leonard Hasenclever, Fabio Pardo, Raia Hadsell, Nicolas Heess, Josh Merel

Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.

Continuous Control reinforcement-learning

Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings

no code implementations9 Dec 2021 Mel Vecerik, Jackie Kay, Raia Hadsell, Lourdes Agapito, Jon Scholz

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics.

Keypoint Detection Object Tracking

Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies

no code implementations ICLR 2022 Dushyant Rao, Fereshteh Sadeghi, Leonard Hasenclever, Markus Wulfmeier, Martina Zambelli, Giulia Vezzani, Dhruva Tirumala, Yusuf Aytar, Josh Merel, Nicolas Heess, Raia Hadsell

We demonstrate in manipulation domains that the method can effectively cluster offline data into distinct, executable behaviours, while retaining the flexibility of a continuous latent variable model.

On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning

no code implementations29 Sep 2021 Abbas Abdolmaleki, Sandy Huang, Giulia Vezzani, Bobak Shahriari, Jost Tobias Springenberg, Shruti Mishra, Dhruva Tirumala, Arunkumar Byravan, Konstantinos Bousmalis, András György, Csaba Szepesvari, Raia Hadsell, Nicolas Heess, Martin Riedmiller

Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional objectives or constraints in the policy optimization step.

Offline RL

Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation

1 code implementation16 Jun 2021 Alex Church, John Lloyd, Raia Hadsell, Nathan F. Lepora

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs.

reinforcement-learning Translation

Learning rich touch representations through cross-modal self-supervision

1 code implementation21 Jan 2021 Martina Zambelli, Yusuf Aytar, Francesco Visin, Yuxiang Zhou, Raia Hadsell

The sense of touch is fundamental in several manipulation tasks, but rarely used in robot manipulation.

Self-Supervised Learning Robotics

Explicit Pareto Front Optimization for Constrained Reinforcement Learning

no code implementations1 Jan 2021 Sandy Huang, Abbas Abdolmaleki, Philemon Brakel, Steven Bohez, Nicolas Heess, Martin Riedmiller, Raia Hadsell

We propose a framework that uses a multi-objective RL algorithm to find a Pareto front of policies that trades off between the reward and constraint(s), and simultaneously searches along this front for constraint-satisfying policies.

Continuous Control reinforcement-learning

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency

no code implementations30 Sep 2020 Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz

In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision.

Image Reconstruction Representation Learning

Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard

1 code implementation6 Aug 2020 Alex Church, John Lloyd, Raia Hadsell, Nathan F. Lepora

Artificial touch would seem well-suited for Reinforcement Learning (RL), since both paradigms rely on interaction with an environment.

reinforcement-learning

Disentangled Cumulants Help Successor Representations Transfer to New Tasks

no code implementations25 Nov 2019 Christopher Grimm, Irina Higgins, Andre Barreto, Denis Teplyashin, Markus Wulfmeier, Tim Hertweck, Raia Hadsell, Satinder Singh

This is in contrast to the state-of-the-art reinforcement learning agents, which typically start learning each new task from scratch and struggle with knowledge transfer.

Transfer Learning

Attention-Privileged Reinforcement Learning

no code implementations19 Nov 2019 Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner

Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space).

reinforcement-learning

Continual Unsupervised Representation Learning

1 code implementation NeurIPS 2019 Dushyant Rao, Francesco Visin, Andrei A. Rusu, Yee Whye Teh, Razvan Pascanu, Raia Hadsell

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially.

Continual Learning Representation Learning

Neural Execution of Graph Algorithms

no code implementations ICLR 2020 Petar Veličković, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

Graph Neural Networks (GNNs) are a powerful representational tool for solving problems on graph-structured inputs.

Stabilizing Transformers for Reinforcement Learning

5 code implementations ICML 2020 Emilio Parisotto, H. Francis Song, Jack W. Rae, Razvan Pascanu, Caglar Gulcehre, Siddhant M. Jayakumar, Max Jaderberg, Raphael Lopez Kaufman, Aidan Clark, Seb Noury, Matthew M. Botvinick, Nicolas Heess, Raia Hadsell

Harnessing the transformer's ability to process long time horizons of information could provide a similar performance boost in partially observable reinforcement learning (RL) domains, but the large-scale transformers used in NLP have yet to be successfully applied to the RL setting.

General Reinforcement Learning Language Modelling +2

Attention Privileged Reinforcement Learning for Domain Transfer

no code implementations25 Sep 2019 Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner

Applying reinforcement learning (RL) to physical systems presents notable challenges, given requirements regarding sample efficiency, safety, and physical constraints compared to simulated environments.

reinforcement-learning

Meta-Learning with Warped Gradient Descent

1 code implementation ICLR 2020 Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell

On the other hand, approaches that try to control a gradient-based update rule typically resort to computing gradients through the learning process to obtain their meta-gradients, leading to methods that can not scale beyond few-shot task adaptation.

Few-Shot Learning

The StreetLearn Environment and Dataset

1 code implementation4 Mar 2019 Piotr Mirowski, Andras Banki-Horvath, Keith Anderson, Denis Teplyashin, Karl Moritz Hermann, Mateusz Malinowski, Matthew Koichi Grimes, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, Raia Hadsell

These datasets cannot be used for decision-making and reinforcement learning, however, and in general the perspective of navigation as an interactive learning task, where the actions and behaviours of a learning agent are learned simultaneously with the perception and planning, is relatively unsupported.

Decision Making

Learning To Follow Directions in Street View

1 code implementation1 Mar 2019 Karl Moritz Hermann, Mateusz Malinowski, Piotr Mirowski, Andras Banki-Horvath, Keith Anderson, Raia Hadsell

Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision.

Success at any cost: value constrained model-free continuous control

no code implementations27 Sep 2018 Steven Bohez, Abbas Abdolmaleki, Michael Neunert, Jonas Buchli, Nicolas Heess, Raia Hadsell

We demonstrate the efficiency of our approach using a number of continuous control benchmark tasks as well as a realistic, energy-optimized quadruped locomotion task.

Continuous Control

Meta-Learning with Latent Embedding Optimization

4 code implementations ICLR 2019 Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, Raia Hadsell

We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space.

Few-Shot Learning

Graph networks as learnable physics engines for inference and control

1 code implementation ICML 2018 Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model.

Progress & Compress: A scalable framework for continual learning

no code implementations ICML 2018 Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell

This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task.

Active Learning Atari Games +1

The Limits and Potentials of Deep Learning for Robotics

no code implementations18 Apr 2018 Niko Sünderhauf, Oliver Brock, Walter Scheirer, Raia Hadsell, Dieter Fox, Jürgen Leitner, Ben Upcroft, Pieter Abbeel, Wolfram Burgard, Michael Milford, Peter Corke

In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning.

Robotics

Learning to Navigate in Cities Without a Map

3 code implementations NeurIPS 2018 Piotr Mirowski, Matthew Koichi Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, Raia Hadsell

We present an interactive navigation environment that uses Google StreetView for its photographic content and worldwide coverage, and demonstrate that our learning method allows agents to learn to navigate multiple cities and to traverse to target destinations that may be kilometres away.

Autonomous Navigation reinforcement-learning

One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

1 code implementation28 Nov 2017 Jake Bruce, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell, Michael Milford

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment.

reinforcement-learning Robot Navigation

Sim-to-Real Robot Learning from Pixels with Progressive Nets

no code implementations13 Oct 2016 Andrei A. Rusu, Mel Vecerik, Thomas Rothörl, Nicolas Heess, Razvan Pascanu, Raia Hadsell

The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills.

reinforcement-learning

Progressive Neural Networks

9 code implementations15 Jun 2016 Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell

Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.

Continual Learning reinforcement-learning

Policy Distillation

1 code implementation19 Nov 2015 Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance.

reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.