Exploration is essential in reinforcement learning, particularly in
envi...
We introduce a new approach to probabilistic unsupervised learning based...
A key goal of unsupervised learning is to go beyond density estimation a...
Efficient reinforcement learning (RL) involves a trade-off between
"expl...
We propose learning via retracing, a novel self-supervised approach for
...
Markovian tasks can be characterised by a state space and a transition
m...