Author name cluster

Misha Denil

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

TMLR Journal 2024 Journal Article

RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation

Konstantinos Bousmalis
Giulia Vezzani
Dushyant Rao
Coline Manon Devin
Alex X. Lee
Maria Bauza Villalonga
Todor Davchev
Yuxiang Zhou

The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by recent advances in foundation models for vision and language, we propose a multi-embodiment, multi-task generalist agent for robotic manipulation. This agent, named RoboCat, is a visual goal-conditioned decision transformer capable of consuming action-labelled visual experience. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100–1000 examples for the target task. We also show how a trained model itself can be used to generate data for subsequent training iterations, thus providing a basic building block for an autonomous improvement loop. We investigate the agent’s capabilities, with large-scale evaluations both in simulation and on three different real robot embodiments. We find that as we grow and diversify its training data, RoboCat not only shows signs of cross-task transfer, but also becomes more efficient at adapting to new tasks.

PDF Details

ICLR Conference 2024 Conference Paper

π2vec: Policy Representation with Successor Features

Gianluca Scarpellini
Ksenia Konyushkova
Claudio Fantacci
Thomas Paine
Yutian Chen 0001
Misha Denil

This paper introduces $\pi$2vec, a method for representing black box policies as comparable feature vectors. Our method combines the strengths of foundation models that serve as generic and powerful state representations and successor features that can model the future occurrence of the states for a policy. $\pi$2vec represents the behavior of policies by capturing the statistics of the features from a pretrained model with the help of successor feature framework. We focus on the offline setting where policies and their representations are trained on a fixed dataset of trajectories. Finally, we employ linear regression on $\pi$2vec vector representations to predict the performance of held out policies. The synergy of these techniques results in a method for efficient policy evaluation in resource constrained environments.

Details

NeurIPS Conference 2021 Conference Paper

Active Offline Policy Selection

Ksenia Konyushova
Yutian Chen
Thomas Paine
Caglar Gulcehre
Cosmin Paduraru
Daniel J. Mankowitz
Misha Denil
Nando de Freitas

This paper addresses the problem of policy selection in domains with abundant logged data, but with a restricted interaction budget. Solving this problem would enable safe evaluation and deployment of offline reinforcement learning policies in industry, robotics, and recommendation domains among others. Several off-policy evaluation (OPE) techniques have been proposed to assess the value of policies using only logged data. However, there is still a big gap between the evaluation by OPE and the full online evaluation in the real environment. Yet, large amounts of online interactions are often not possible in practice. To overcome this problem, we introduce active offline policy selection --- a novel sequential decision approach that combines logged data with online interaction to identify the best policy. This approach uses OPE estimates to warm start the online evaluation. Then, in order to utilize the limited environment interactions wisely we decide which policy to evaluate next based on a Bayesian optimization method with a kernel function that represents policy similarity. We use multiple benchmarks with a large number of candidate policies to show that the proposed approach improves upon state-of-the-art OPE estimates and pure online policy evaluation.

PDF Details

ICLR Conference 2020 Conference Paper

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

Çaglar Gülçehre
Tom Le Paine
Bobak Shahriari
Misha Denil
Matthew Hoffman 0002
Hubert Soyer
Richard Tanburn
Steven Kapturowski

This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions. We also introduce a suite of eight tasks that combine these three properties, and show that R2D3 can solve several of the tasks where other state of the art methods (both with and without demonstrations) fail to see even a single successful trajectory after tens of billions of steps of exploration.

Details

ICML Conference 2017 Conference Paper

Learned Optimizers that Scale and Generalize

Olga Wichrowska
Niru Maheswaranathan
Matthew Hoffman 0002
Sergio Gomez Colmenarejo
Misha Denil
Nando de Freitas
Jascha Sohl-Dickstein

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 well to new tasks, and which has significantly reduced memory and computation overhead. We achieve this by introducing a novel hierarchical RNN architecture, with minimal per-parameter overhead, augmented with additional architectural features that mirror the known structure of optimization tasks. We also develop a meta-training ensemble of small, diverse, optimization tasks capturing common properties of loss landscapes. The optimizer learns to outperform RMSProp/ADAM on problems in this corpus. More importantly, it performs comparably or better when applied to small convolutional neural networks, despite seeing no neural networks in its meta-training set. Finally, it generalizes to train Inception V3 and ResNet V2 architectures on the ImageNet dataset for thousands of steps, optimization problems that are of a vastly different scale than those it was trained on.

Details

ICML Conference 2017 Conference Paper

Learning to Learn without Gradient Descent by Gradient Descent

Yutian Chen 0001
Matthew Hoffman 0002
Sergio Gomez Colmenarejo
Misha Denil
Timothy P. Lillicrap
Matthew M. Botvinick
Nando de Freitas

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 Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-parameter tuning tasks. Up to the training horizon, the learned optimizers learn to trade-off exploration and exploitation, and compare favourably with heavily engineered Bayesian optimization packages for hyper-parameter tuning.

Details

NeurIPS Conference 2016 Conference Paper

Learning to learn by gradient descent by gradient descent

Marcin Andrychowicz
Misha Denil
Sergio Gómez
Matthew Hoffman
David Pfau
Tom Schaul
Brendan Shillingford
Nando de Freitas

The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this, optimization algorithms are still designed by hand. In this paper we show how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way. Our learned algorithms, implemented by LSTMs, outperform generic, hand-designed competitors on the tasks for which they are trained, and also generalize well to new tasks with similar structure. We demonstrate this on a number of tasks, including simple convex problems, training neural networks, and styling images with neural art.

PDF Details

ICML Conference 2016 Conference Paper

Noisy Activation Functions

Çaglar Gülçehre
Marcin Moczulski
Misha Denil
Yoshua Bengio

Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions to emulate the discrete switching of digital logic circuits are good examples of this. We propose to exploit the injection of appropriate noise so that the gradients may flow easily, even if the noiseless application of the activation function would yield zero gradients. Large noise will dominate the noise-free gradient and allow stochastic gradient descent to explore more. By adding noise only to the problematic parts of the activation function, we allow the optimization procedure to explore the boundary between the degenerate saturating) and the well-behaved parts of the activation function. We also establish connections to simulated annealing, when the amount of noise is annealed down, making it easier to optimize hard objective functions. We find experimentally that replacing such saturating activation functions by noisy variants helps optimization in many contexts, yielding state-of-the-art or competitive results on different datasets and task, especially when training seems to be the most difficult, e. g. , when curriculum learning is necessary to obtain good results.

Details

NeurIPS Conference 2014 Conference Paper

Distributed Parameter Estimation in Probabilistic Graphical Models

Yariv Mizrahi
Misha Denil
Nando de Freitas

This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.

PDF Details

ICML Conference 2014 Conference Paper

Linear and Parallel Learning of Markov Random Fields

Yariv Dror Mizrahi
Misha Denil
Nando de Freitas

We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields which is efficient for a large class of practical models. Our algorithm parallelizes naturally over cliques and, for graphs of bounded degree, its complexity is linear in the number of cliques. Unlike its competitors, our algorithm is fully parallel and for log-linear models it is also data efficient, requiring only the local sufficient statistics of the data to estimate parameters.

Details

ICML Conference 2014 Conference Paper

Narrowing the Gap: Random Forests In Theory and In Practice

Misha Denil
David Matheson
Nando de Freitas

Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood. In this paper we contribute to this understanding in two ways. We present a new theoreti- cally tractable variant of random regression forests and prove that our algorithm is con- sistent. We also provide an empirical eval- uation, comparing our algorithm and other theoretically tractable random forest models to the random forest algorithm used in prac- tice. Our experiments provide insight into the relative importance of different simplifi- cations that theoreticians have made to ob- tain tractable models for analysis.

Details

ICML Conference 2013 Conference Paper

Consistency of Online Random Forests

Misha Denil
David Matheson
Nando de Freitas

As a testament to their success, the theory of random forests has long been outpaced by their application in practice. In this paper, we take a step towards narrowing this gap by providing a consistency result for online random forests.

Details

NeurIPS Conference 2013 Conference Paper

Predicting Parameters in Deep Learning

Misha Denil
Babak Shakibi
Laurent Dinh
Marc'Aurelio Ranzato
Nando de Freitas

We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be learned at all. We train several different architectures by learning only a small number of weights and predicting the rest. In the best case we are able to predict more than 95% of the weights of a network without any drop in accuracy.

PDF Details