Search Results for author:
Found 33 papers, 12 papers with code
Gaussian Gated Linear Networks
We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks.
Interval timing in deep reinforcement learning agents
The measurement of time is central to intelligent behavior.
Synthetic Returns for Long-Term Credit Assignment
We propose state-associative (SA) learning, where the agent learns associations between states and arbitrarily distant future rewards, then propagates credit directly between the two.
Learning Continuous Control Policies by Stochastic Value Gradients
One of these variants, SVG(1), shows the effectiveness of learning models, value functions, and policies simultaneously in continuous domains.
Neural Turing Machines
We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes.
Emergence of Locomotion Behaviours in Rich Environments
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals.
Associative Long Short-Term Memory
We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters.
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.
Learning human behaviors from motion capture by adversarial imitation
Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies.
Unsupervised Predictive Memory in a Goal-Directed Agent
Animals execute goal-directed behaviours despite the limited range and scope of their sensors.
Hindsight Credit Assignment
We consider the problem of efficient credit assignment in reinforcement learning.
The Kanerva Machine: A Generative Distributed Memory
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them.
Probing Physics Knowledge Using Tools from Developmental Psychology
While some work on this problem has taken the approach of building in components such as ready-made physics engines, other research aims to extract general physical concepts directly from sensory data.
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.
Generative Temporal Models with Memory
We consider the general problem of modeling temporal data with long-range dependencies, wherein new observations are fully or partially predictable based on temporally-distant, past observations.
Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes
SAM learns with comparable data efficiency to existing models on a range of synthetic tasks and one-shot Omniglot character recognition, and can scale to tasks requiring $100,\! 000$s of time steps and memories.
Ranked #6 on
Question Answering
on bAbi
(Mean Error Rate metric)
Learning and Transfer of Modulated Locomotor Controllers
We study a novel architecture and training procedure for locomotion tasks.
Towards an integration of deep learning and neuroscience
We hypothesize that (1) the brain optimizes cost functions, (2) these cost functions are diverse and differ across brain locations and over development, and (3) optimization operates within a pre-structured architecture matched to the computational problems posed by behavior.
Neurons and Cognition
Optimizing Agent Behavior over Long Time Scales by Transporting Value
Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel".
Hierarchical visuomotor control of humanoids
We aim to build complex humanoid agents that integrate perception, motor control, and memory.
Neural probabilistic motor primitives for humanoid control
We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids.
Experience Replay for Continual Learning
We examine this issue in the context of reinforcement learning, in a setting where an agent is exposed to tasks in a sequence.
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reusable structure in solution space is likely to become increasingly important.
Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks
We address the longstanding challenge of producing flexible, realistic humanoid character controllers that can perform diverse whole-body tasks involving object interactions.
Deep neuroethology of a virtual rodent
In this work, we develop a virtual rodent as a platform for the grounded study of motor activity in artificial models of embodied control.
Product Kanerva Machines: Factorized Bayesian Memory
An ideal cognitively-inspired memory system would compress and organize incoming items.
Imitating Interactive Intelligence
These evaluations convincingly demonstrate that interactive training and auxiliary losses improve agent behaviour beyond what is achieved by supervised learning of actions alone.
Imitation by Predicting Observations
Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior.
Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language.
Evaluating Multimodal Interactive Agents
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research.
Replay and compositional computation
Replay in the brain has been viewed as rehearsal, or, more recently, as sampling from a transition model.
Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback
Here we demonstrate how to use reinforcement learning from human feedback (RLHF) to improve upon simulated, embodied agents trained to a base level of competency with imitation learning.
