research
∙
05/24/2023
Successor-Predecessor Intrinsic Exploration
Exploration is essential in reinforcement learning, particularly in envi...
share
research
∙
09/12/2022
FP8 Formats for Deep Learning
FP8 is a natural progression for accelerating deep learning training inf...
research
∙
09/12/2022
Amortised Inference in Structured Generative Models with Explaining Away
A key goal of unsupervised learning is to go beyond density estimation a...
research
∙
05/30/2022
SEREN: Knowing When to Explore and When to Exploit
Efficient reinforcement learning (RL) involves a trade-off between "expl...
research
∙
11/24/2021
Learning State Representations via Retracing in Reinforcement Learning
We propose learning via retracing, a novel self-supervised approach for ...
research
∙
06/05/2020
Prediction with directed transitions: complex eigenstructure, grid cells and phase coding
Markovian tasks can be characterised by a state space and a transition m...
research
∙
10/06/2019