Search Results for author:
Found 76 papers, 32 papers with code
Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning
However, due to safety, ethical, and practicality constraints, this type of trial-and-error experimentation is often infeasible in many real-world domains such as healthcare and robotics.
Vision-Language Models as Success Detectors
Detecting successful behaviour is crucial for training intelligent agents.
Multi-step Planning for Automated Hyperparameter Optimization with OptFormer
As machine learning permeates more industries and models become more expensive and time consuming to train, the need for efficient automated hyperparameter optimization (HPO) has never been more pressing.
Towards Learning Universal Hyperparameter Optimizers with Transformers
Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar distribution.
A Generalist Agent
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs.
Ranked #1 on
Skill Generalization
on RGB-Stacking
Restoring and attributing ancient texts using deep neural networks
Ithaca can attribute inscriptions to their original location with an accuracy of 71% and can date them to less than 30 years of their ground-truth ranges, redating key texts of Classical Athens and contributing to topical debates in ancient history.
Ranked #1 on
Ancient Text Restoration
on I.PHI
Competition-Level Code Generation with AlphaCode
Programming is a powerful and ubiquitous problem-solving tool.
Ranked #1 on
Code Generation
on CodeContests
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
Active Offline Policy Selection
We use multiple benchmarks, including real-world robotics, 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.
On Instrumental Variable Regression for Deep Offline Policy Evaluation
By applying different IV techniques to OPE, we are not only able to recover previously proposed OPE methods such as model-based techniques but also to obtain competitive new techniques.
Regularized Behavior Value Estimation
Due to bootstrapping, these errors get amplified during training and can lead to divergence, thereby crippling learning.
Addressing Extrapolation Error in Deep Offline Reinforcement Learning
These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning.
Semi-supervised reward learning for offline reinforcement learning
In offline reinforcement learning (RL) agents are trained using a logged dataset.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Offline Learning from Demonstrations and Unlabeled Experience
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
Large-scale multilingual audio visual dubbing
The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language.
Learning Deep Features in Instrumental Variable Regression
We propose a novel method, deep feature instrumental variable regression (DFIV), to address the case where relations between instruments, treatments, and outcomes may be nonlinear.
Learning Compositional Neural Programs for Continuous Control
Third, the self-models are harnessed to learn recursive compositional programs with multiple levels of abstraction.
Hyperparameter Selection for Offline Reinforcement Learning
Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i. e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data.
Critic Regularized Regression
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction.
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Acme: A Research Framework for Distributed Reinforcement Learning
These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.
Task-Relevant Adversarial Imitation Learning
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.
Scaling data-driven robotics with reward sketching and batch reinforcement learning
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
Modular Meta-Learning with Shrinkage
Many real-world problems, including multi-speaker text-to-speech synthesis, can greatly benefit from the ability to meta-learn large models with only a few task-specific components.
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
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.
Learning Compositional Neural Programs with Recursive Tree Search and Planning
AlphaZero contributes powerful neural network guided search algorithms, which we augment with recursion.
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward.
Bayesian Optimization in AlphaGo
During the development of AlphaGo, its many hyper-parameters were tuned with Bayesian optimization multiple times.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
MetaMimic can learn both (i) policies for high-fidelity one-shot imitation of diverse novel skills, and (ii) policies that enable the agent to solve tasks more efficiently than the demonstrators.
Sample Efficient Adaptive Text-to-Speech
Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers.
Large-Scale Visual Speech Recognition
To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking (3, 886 hours of video).
Ranked #10 on
Lipreading
on LRS3-TED
(using extra training data)
Playing hard exploration games by watching YouTube
One successful method of guiding exploration in these domains is to imitate trajectories provided by a human demonstrator.
Hyperbolic Attention Networks
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
Learning Awareness Models
We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
Compositional Obverter Communication Learning From Raw Visual Input
Previously, it has been shown that neural network agents can learn to communicate in a highly structured, possibly compositional language based on disentangled input (e. g. hand- engineered features).
Reinforcement and Imitation Learning for Diverse Visuomotor Skills
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent.
Cortical microcircuits as gated-recurrent neural networks
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas.
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Deep autoregressive models have shown state-of-the-art performance in density estimation for natural images on large-scale datasets such as ImageNet.
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
This paper introduces the Intentional Unintentional (IU) agent.
Robust Imitation of Diverse Behaviors
Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more robust controllers from fewer demonstrations, but is inherently mode-seeking and more difficult to train.
Programmable Agents
We build deep RL agents that execute declarative programs expressed in formal language.
Learned Optimizers that Scale and Generalize
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.
Parallel Multiscale Autoregressive Density Estimation
Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.
Ranked #2 on
Image Compression
on ImageNet32
Learning to Learn without Gradient Descent by Gradient Descent
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent.
Learning to Perform Physics Experiments via Deep Reinforcement Learning
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way.
LipNet: End-to-End Sentence-level Lipreading
Lipreading is the task of decoding text from the movement of a speaker's mouth.
Ranked #5 on
Lipreading
on GRID corpus (mixed-speech)
Sample Efficient Actor-Critic with Experience Replay
This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.
Learning to learn by gradient descent by gradient descent
The move from hand-designed features to learned features in machine learning has been wildly successful.
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility.
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks
We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks.
Dueling Network Architectures for Deep Reinforcement Learning
In recent years there have been many successes of using deep representations in reinforcement learning.
Ranked #1 on
Atari Games
on Atari 2600 Pong
Neural Programmer-Interpreters
We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs.
ACDC: A Structured Efficient Linear Layer
Finally, this paper also provides a connection between structured linear transforms used in deep learning and the field of Fourier optics, illustrating how ACDC could in principle be implemented with lenses and diffractive elements.
Unbounded Bayesian Optimization via Regularization
Bayesian optimization has recently emerged as a popular and efficient tool for global optimization and hyperparameter tuning.
Deep Fried Convnets
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters.
Ranked #55 on
Image Classification
on MNIST
Extraction of Salient Sentences from Labelled Documents
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure.
Deep Multi-Instance Transfer Learning
We present a new approach for transferring knowledge from groups to individuals that comprise them.
Heteroscedastic Treed Bayesian Optimisation
At the core of this approach is a Gaussian process prior that captures our belief about the distribution over functions.
Theoretical Analysis of Bayesian Optimisation with Unknown Gaussian Process Hyper-Parameters
Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models.
An Entropy Search Portfolio for Bayesian Optimization
How- ever, the performance of a Bayesian optimization method very much depends on its exploration strategy, i. e. the choice of acquisition function, and it is not clear a priori which choice will result in superior performance.
Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval.
Distributed Parameter Estimation in Probabilistic Graphical Models
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models.
A Deep Architecture for Semantic Parsing
Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries.
Bayesian Multi-Scale Optimistic Optimization
In this paper, we introduce a new technique for efficient global optimization that combines Gaussian process confidence bounds and treed simultaneous optimistic optimization to eliminate the need for auxiliary optimization of acquisition functions.
Narrowing the Gap: Random Forests In Theory and In Practice
Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood.
Linear and Parallel Learning of Markov Random Fields
We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models.
Predicting Parameters in Deep Learning
We demonstrate that there is significant redundancy in the parameterization of several deep learning models.
Exploiting correlation and budget constraints in Bayesian multi-armed bandit optimization
This problem is also known as fixed-budget best arm identification in the multi-armed bandit literature.
Consistency of Online Random Forests
As a testament to their success, the theory of random forests has long been outpaced by their application in practice.
Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (2012)
This is the Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence, which was held on Catalina Island, CA August 14-18 2012.
Variational MCMC
One of these algorithms is a mixture of two MCMC kernels: a random walk Metropolis kernel and a blockMetropolis-Hastings (MH) kernel with a variational approximation as proposaldistribution.
Bayesian Optimization in a Billion Dimensions via Random Embeddings
Bayesian optimization techniques have been successfully applied to robotics, planning, sensor placement, recommendation, advertising, intelligent user interfaces and automatic algorithm configuration.
A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
We present a tutorial on Bayesian optimization, a method of finding the maximum of expensive cost functions.
Bayesian Optimization
Hierarchical Reinforcement Learning
+3
