Asymmetric Norms to Approximate the Minimum Action Distance

1 code implementation • 16 Dec 2023 • Lorenzo Steccanella, Anders Jonsson

Our results show that our asymmetric norm parametrization performs comparably to symmetric norms in symmetric environments and surpasses symmetric norms in asymmetric environments.

State Representation Learning for Goal-Conditioned Reinforcement Learning

no code implementations • 4 May 2022 • Lorenzo Steccanella, Anders Jonsson

This paper presents a novel state representation for reward-free Markov decision processes.

reinforcement-learning Reinforcement Learning (RL) +1

Hierarchical Representation Learning for Markov Decision Processes

no code implementations • 3 Jun 2021 • Lorenzo Steccanella, Simone Totaro, Anders Jonsson

In this paper we present a novel method for learning hierarchical representations of Markov decision processes.

Representation Learning

Hierarchical reinforcement learning for efficient exploration and transfer

no code implementations • 12 Nov 2020 • Lorenzo Steccanella, Simone Totaro, Damien Allonsius, Anders Jonsson

Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time.

Efficient Exploration Hierarchical Reinforcement Learning +2

Hierarchical reinforcement learning for efficent exploration and transfer

no code implementations • ICML Workshop LifelongML 2020 • Lorenzo Steccanella, Simone Totaro, Damien Allonsius, Anders Jonsson

Sparse-reward domains are challenging for reinforcement learning algorithms since significant exploration is needed before encountering reward for the first time.

Hierarchical Reinforcement Learning reinforcement-learning +1