Search Results for author:
Found 25 papers, 9 papers with code
Scaling Instructable Agents Across Many Simulated Worlds
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI.
Human-Timescale Adaptation in an Open-Ended Task Space
Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning (RL).
Evolving Neural Update Rules for Sequence Learning
We consider the problem of searching, end to end, for effective weight and activation update rules governing online learning of a recurrent network on problems of character sequence memorisation and prediction.
Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
We propose an artificial life framework aimed at facilitating the emergence of intelligent organisms.
Finding online neural update rules by learning to remember
We investigate learning of the online local update rules for neural activations (bodies) and weights (synapses) from scratch.
Causally Correct Partial Models for Reinforcement Learning
In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions.
Shaping Belief States with Generative Environment Models for RL
We propose a way to efficiently train expressive generative models in complex environments.
An investigation of model-free planning
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity.
Learning Attractor Dynamics for Generative Memory
Based on the idea of memory writing as inference, as proposed in the Kanerva Machine, we show that a likelihood-based Lyapunov function emerges from maximising the variational lower-bound of a generative memory.
Temporal Difference Variational Auto-Encoder
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction.
Learning and Querying Fast Generative Models for Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Learning Dynamic State Abstractions for Model-Based Reinforcement Learning
A key challenge in model-based reinforcement learning (RL) is to synthesize computationally efficient and accurate environment models.
Variational Intrinsic Control
In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent.
Reinforcement Learning (RL)
Unsupervised Reinforcement Learning
What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures?
We also introduce a new single phase supervised learning procedure that places an L1 penalty on the output state of each layer of the network.
Neural Autoregressive Distribution Estimation
We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation.
Towards Conceptual Compression
We introduce a simple recurrent variational auto-encoder architecture that significantly improves image modeling.
Ranked #64 on
Image Generation
on CIFAR-10
(bits/dimension metric)
One-Shot Generalization in Deep Generative Models
In particular, humans have an ability for one-shot generalization: an ability to encounter a new concept, understand its structure, and then be able to generate compelling alternative variations of the concept.
Towards Principled Unsupervised Learning
Supervised learning is successful because it can be solved by the minimization of the training error cost function.
DRAW: A Recurrent Neural Network For Image Generation
This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation.
Ranked #70 on
Image Generation
on CIFAR-10
(bits/dimension metric)
MADE: Masked Autoencoder for Distribution Estimation
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples.
Ranked #4 on
Density Estimation
on UCI GAS
Neural Variational Inference and Learning in Belief Networks
Highly expressive directed latent variable models, such as sigmoid belief networks, are difficult to train on large datasets because exact inference in them is intractable and none of the approximate inference methods that have been applied to them scale well.
Deep AutoRegressive Networks
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data.
A lattice filter model of the visual pathway
Early stages of visual processing are thought to decorrelate, or whiten, the incoming temporally varying signals.
Structured sparse coding via lateral inhibition
This work describes a conceptually simple method for structured sparse coding and dictionary design.
Learning Convolutional Feature Hierarchies for Visual Recognition
We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features.
