159 citations · 329 across the 29 of their papers we have counts for
32 papers
Evaluation Metrics for Safe Reinforcement Learning
Lindsay Spoor, Aske Plaat, Thomas Moerland
Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its expected cumu…
Guiding Skill Discovery with Foundation Models
Zhao Yang, Thomas M. Moerland, Mike Preuss +3
Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on…
A Unified Framework for Zero-Shot Reinforcement Learning
Jacopo Di Ventura, Jan Felix Kleuker, Aske Plaat +1
Zero-shot reinforcement learning (RL) has emerged as a setting for developing general agents, capable of solving downstream tasks without additional training or planning at test-ti…
Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning
Lindsay Spoor, Álvaro Serra-Gómez, Aske Plaat +1
Safe reinforcement learning addresses constrained optimization problems where maximizing performance must be balanced against safety constraints, and Lagrangian methods are a widel…
On the Effect of Regularization in Policy Mirror Descent
Jan Felix Kleuker, Aske Plaat, Thomas Moerland
Policy Mirror Descent (PMD) has emerged as a unifying framework in reinforcement learning (RL) by linking policy gradient methods with a first-order optimization method known as mi…
Chargax: A JAX Accelerated EV Charging Simulator
Koen Ponse, Jan Felix Kleuker, Aske Plaat +1
Deep Reinforcement Learning can play a key role in addressing sustainable energy challenges. For instance, many grid systems are heavily congested, highlighting the urgent need to…
EconoJax: A Fast & Scalable Economic Simulation in Jax
Koen Ponse, Aske Plaat, Niki van Stein +1
Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in…
Reset-free Reinforcement Learning with World Models
Zhao Yang, Thomas M. Moerland, Mike Preuss +2
Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, th…
Reinforcement Learning for Sustainable Energy: A Survey
Koen Ponse, Felix Kleuker, Márton Fejér +3
The transition to sustainable energy is a key challenge of our time, requiring modifications in the entire pipeline of energy production, storage, transmission, and consumption. At…
Towards General Negotiation Strategies with End-to-End Reinforcement Learning
Bram M. Renting, Thomas M. Moerland, Holger H. Hoos +1
The research field of automated negotiation has a long history of designing agents that can negotiate with other agents. Such negotiation strategies are traditionally based on manu…
Slot Structured World Models
Jonathan Collu, Riccardo Majellaro, Aske Plaat +1
The ability to perceive and reason about individual objects and their interactions is a goal to be achieved for building intelligent artificial systems. State-of-the-art approaches…
Explicitly Disentangled Representations in Object-Centric Learning
Riccardo Majellaro, Jonathan Collu, Aske Plaat +1
Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object…
EduGym: An Environment and Notebook Suite for Reinforcement Learning Education
Thomas M. Moerland, Matthias Müller-Brockhausen, Zhao Yang +7
Due to the empirical success of reinforcement learning, an increasing number of students study the subject. However, from our practical teaching experience, we see students enterin…
Are LSTMs Good Few-Shot Learners?
Mike Huisman, Thomas M. Moerland, Aske Plaat +1
Deep learning requires large amounts of data to learn new tasks well, limiting its applicability to domains where such data is available. Meta-learning overcomes this limitation by…
What model does MuZero learn?
Jinke He, Thomas M. Moerland, Joery A. de Vries +1
Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models,…
Two-Memory Reinforcement Learning
Zhao Yang, Thomas. M. Moerland, Mike Preuss +1
While deep reinforcement learning has shown important empirical success, it tends to learn relatively slow due to slow propagation of rewards information and slow update of paramet…
First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation
Zhao Yang, Thomas M. Moerland, Mike Preuss +1
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards. The key insight of Go-Explore was that successful exploration req…
Continuous Episodic Control
Zhao Yang, Thomas M. Moerland, Mike Preuss +1
Non-parametric episodic memory can be used to quickly latch onto high-rewarded experience in reinforcement learning tasks. In contrast to parametric deep reinforcement learning app…
When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
Zhao Yang, Thomas M. Moerland, Mike Preuss +1
Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards. The key insight of Go-Explore was that successful exploration req…
On Credit Assignment in Hierarchical Reinforcement Learning
Joery A. de Vries, Thomas M. Moerland, Aske Plaat
Hierarchical Reinforcement Learning (HRL) has held longstanding promise to advance reinforcement learning. Yet, it has remained a considerable challenge to develop practical algori…
Visualizing MuZero Models
Joery A. de Vries, Ken S. Voskuil, Thomas M. Moerland +1
MuZero, a model-based reinforcement learning algorithm that uses a value equivalent dynamics model, achieved state-of-the-art performance in Chess, Shogi and the game of Go. In con…
Model-based Reinforcement Learning: A Survey
Thomas M. Moerland, Joost Broekens, Aske Plaat +1
Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is a important challenge in artificial intelligence. Two key approaches to this probl…
A Unifying Framework for Reinforcement Learning and Planning
Thomas M. Moerland, Joost Broekens, Aske Plaat +1
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimi…
The Second Type of Uncertainty in Monte Carlo Tree Search
Thomas M Moerland, Joost Broekens, Aske Plaat +1
Monte Carlo Tree Search (MCTS) efficiently balances exploration and exploitation in tree search based on count-derived uncertainty. However, these local visit counts ignore a secon…