Hierarchical reinforcement learning for efficient exploration and transfer

By Lorenzo Steccanella, Simone Totaro, Damien Allonsius, Anders Jonsson. 2020

10 citations recorded by the source corpus.

Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time. Hierarchical reinforcement learning can facilitate exploration by reducing the number of decisions necessary before obtaining a reward. In this paper, we present a novel hierarchical reinforcement learning framework based on the compression of an invariant state space that is common to a range of tasks. The algorithm introduces subtasks which consist of moving between the state partitions induced by the compression. Results indicate that the algorithm can successfully solve complex sparse-reward domains, and transfer knowledge to solve new, previously unseen tasks more quickly.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Piotr Milo's
2. Lukasz Kuci'nski
3. Maciej Wolczyk
4. Michal Zajkac
5. Razvan Pascanu
6. Yoshua Bengio
7. Kyunghyun Cho
8. Sergey Levine

In Cognitive Neuroscience

1. Razvan Pascanu
2. Lukasz Kuci'nski
3. Piotr Milo's
4. Maciej Wolczyk
5. Michal Zajkac

In Molecular Biology

1. Razvan Pascanu

Citations in the corpus

• Disentangling Transfer in Continual Reinforcement Learning (2022, background): “[27, 39] achieve transfer by means of high-level skills and hierarchical RL.”