7 papers
Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification
Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi +1
We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact t…
Coordination Graphs for Constrained Multi-Agent Reinforcement Learning
Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson
Constrained Multi-agent reinforcement learning (CMARL) faces two intertwined challenges: the joint action space grows exponentially with the number of agents, and additional requir…
Scalable Constrained Multi-Agent Reinforcement Learning via State Augmentation and Consensus for Separable Dynamics
Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson
We present a distributed approach for constrained Multi-Agent Reinforcement Learning (MARL) that combines state-augmented policy learning with distributed consensus over dual varia…
The Terminal Representation in Reinforcement Learning
Amir Esterhuysen, Anders Jonsson
Representation learning is a powerful tool for spatio-temporal abstraction within reinforcement learning (RL). Two well established approaches are through the successor representat…
Sampling-guided exploration of active feature selection policies
Gabriel Bernardino, Anders Jonsson, Patrick Clarysse +1
Determining the most appropriate features for machine learning predictive models is challenging regarding performance and feature acquisition costs. In particular, global feature c…
Learning The Minimum Action Distance
Lorenzo Steccanella, Joshua B. Evans, Özgür Şimşek +1
This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor t…
Asymmetric Norms to Approximate the Minimum Action Distance
Lorenzo Steccanella, Anders Jonsson
This paper presents a state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between…