research
∙
10/01/2021
Powerpropagation: A sparsity inducing weight reparameterisation
The training of sparse neural networks is becoming an increasingly impor...
share
research
∙
06/07/2021
Top-KAST: Top-K Always Sparse Training
Sparse neural networks are becoming increasingly important as the field ...
research
∙
06/26/2020
Perception-Prediction-Reaction Agents for Deep Reinforcement Learning
We introduce a new recurrent agent architecture and associated auxiliary...
research
∙
11/13/2019
Compressive Transformers for Long-Range Sequence Modelling
We present the Compressive Transformer, an attentive sequence model whic...
research
∙
10/13/2019
Stabilizing Transformers for Reinforcement Learning
Owing to their ability to both effectively integrate information over lo...
research
∙
05/08/2019
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for buildi...
research
∙
05/03/2019
Information asymmetry in KL-regularized RL
Many real world tasks exhibit rich structure that is repeated across dif...
research
∙
02/06/2019
Distilling Policy Distillation
The transfer of knowledge from one policy to another is an important too...
research
∙
12/05/2018
Adapting Auxiliary Losses Using Gradient Similarity
One approach to deal with the statistical inefficiency of neural network...
research
∙
06/05/2018
Mix&Match - Agent Curricula for Reinforcement Learning
We introduce Mix&Match (M&M) - a training framework designed to facilita...
research
∙
05/24/2018
Been There, Done That: Meta-Learning with Episodic Recall
Meta-learning agents excel at rapidly learning new tasks from open-ended...
research
∙
05/13/2018
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Reinforcement learning (RL) agents performing complex tasks must be able...
research
∙
02/28/2018