Thomas M. Moerland
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Thomas M. Moerland has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Aske Plaat
Leiden Institute of Advanced Computer Science Leiden University The Netherlands
3 shared publicationsCatholijn M. Jonker
LIACS, Leiden University
2 shared publicationsJoost Broekens
LIACS, Leiden University
2 shared publications- Aske Plaat
LIACS, Leiden University, Leiden, Netherlands
1 shared publication - Jan N. van Rijn
Leiden University, Leiden, The Netherlands
1 shared publication Jonathan Collu
Leiden Institute of Advanced Computer Science Leiden University The Netherlands
1 shared publication
Latest Publications
- Open Access
Slot Structured World Models
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 use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. However, the feedforward encoder can not extract {\it object-centric} representations, nor can it disentangle multiple objects with similar appearance. To solve these issues, we introduce {\it Slot Structured World Models} (SSWM), a class of world models that combines an {\it object-centric} encoder (based on Slot Attention) with a latent graph-based dynamics model. We evaluate our method in the Spriteworld benchmark with simple rules of physical interaction, where Slot Structured World Models consistently outperform baselines on a range of (multi-step) prediction tasks with action-conditional object interactions. All code to reproduce paper experiments is available from \url{https://github.com/JonathanCollu/Slot-Structured-World-Models}.
Open AccessSlot Structured World Models
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 use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. However, the feedforward encoder can not extract {\it object-centric} representations, nor can it disentangle multiple objects with similar appearance. To solve these issues, we introduce {\it Slot Structured World Models} (SSWM), a class of world models that combines an {\it object-centric} encoder (based on Slot Attention) with a latent graph-based dynamics model. We evaluate our method in the Spriteworld benchmark with simple rules of physical interaction, where Slot Structured World Models consistently outperform baselines on a range of (multi-step) prediction tasks with action-conditional object interactions. All code to reproduce paper experiments is available from \url{https://github.com/JonathanCollu/Slot-Structured-World-Models}.
- Open Access
- 7 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4635-4662
Are LSTMs good few-shot learners?
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 learning how to learn. Hochreiter et al. (International conference on artificial neural networks, Springer, 2001) showed that an LSTM trained with backpropagation across different tasks is capable of meta-learning. Despite promising results of this approach on small problems, and more recently, also on reinforcement learning problems, the approach has received little attention in the supervised few-shot learning setting. We revisit this approach and test it on modern few-shot learning benchmarks. We find that LSTM, surprisingly, outperform the popular meta-learning technique MAML on a simple few-shot sine wave regression benchmark, but that LSTM, expectedly, fall short on more complex few-shot image classification benchmarks. We identify two potential causes and propose a new method called Outer Product LSTM (OP-LSTM) that resolves these issues and displays substantial performance gains over the plain LSTM. Compared to popular meta-learning baselines, OP-LSTM yields competitive performance on within-domain few-shot image classification, and performs better in cross-domain settings by 0.5–1.9% in accuracy score. While these results alone do not set a new state-of-the-art, the advances of OP-LSTM are orthogonal to other advances in the field of meta-learning, yield new insights in how LSTM work in image classification, allowing for a whole range of new research directions. For reproducibility purposes, we publish all our research code publicly.
- 7 September 2023
- Published by Springer Nature in Machine Learning
- Vol. 112 (11) , 4635-4662
Open AccessAre LSTMs good few-shot learners?
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 learning how to learn. Hochreiter et al. (International conference on artificial neural networks, Springer, 2001) showed that an LSTM trained with backpropagation across different tasks is capable of meta-learning. Despite promising results of this approach on small problems, and more recently, also on reinforcement learning problems, the approach has received little attention in the supervised few-shot learning setting. We revisit this approach and test it on modern few-shot learning benchmarks. We find that LSTM, surprisingly, outperform the popular meta-learning technique MAML on a simple few-shot sine wave regression benchmark, but that LSTM, expectedly, fall short on more complex few-shot image classification benchmarks. We identify two potential causes and propose a new method called Outer Product LSTM (OP-LSTM) that resolves these issues and displays substantial performance gains over the plain LSTM. Compared to popular meta-learning baselines, OP-LSTM yields competitive performance on within-domain few-shot image classification, and performs better in cross-domain settings by 0.5–1.9% in accuracy score. While these results alone do not set a new state-of-the-art, the advances of OP-LSTM are orthogonal to other advances in the field of meta-learning, yield new insights in how LSTM work in image classification, allowing for a whole range of new research directions. For reproducibility purposes, we publish all our research code publicly.
- Top Cited PapersOpen Access
- 4 January 2023
- Published by Emerald Publishing in Foundations and Trends in Machine Learning
- Vol. 16 (1) , 1-118
Model-based Reinforcement Learning: A Survey
Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is an important challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This survey is an integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover approaches to dynamics model learning, including challenges like dealing with stochasticity, uncertainty, partial observability, and temporal abstraction. Second, we present a systematic categorization of planning-learning integration, including aspects like: where to start planning, what budgets to allocate to planning and real data collection, how to plan, and how to integrate planning in the learning and acting loop. After these two sections, we also discuss implicit model-based RL as an end-to-end alternative for model learning and planning, and we cover the potential benefits of model-based RL. Along the way, the survey also draws connections to several related RL fields, like hierarchical RL and transfer learning. Altogether, the survey presents a broad conceptual overview of the combination of planning and learning for MDP optimization.
- 4 January 2023
- Published by Emerald Publishing in Foundations and Trends in Machine Learning
- Vol. 16 (1) , 1-118
Top Cited PapersOpen AccessModel-based Reinforcement Learning: A Survey
Sequential decision making, commonly formalized as Markov Decision Process (MDP) optimization, is an important challenge in artificial intelligence. Two key approaches to this problem are reinforcement learning (RL) and planning. This survey is an integration of both fields, better known as model-based reinforcement learning. Model-based RL has two main steps. First, we systematically cover approaches to dynamics model learning, including challenges like dealing with stochasticity, uncertainty, partial observability, and temporal abstraction. Second, we present a systematic categorization of planning-learning integration, including aspects like: where to start planning, what budgets to allocate to planning and real data collection, how to plan, and how to integrate planning in the learning and acting loop. After these two sections, we also discuss implicit model-based RL as an end-to-end alternative for model learning and planning, and we cover the potential benefits of model-based RL. Along the way, the survey also draws connections to several related RL fields, like hierarchical RL and transfer learning. Altogether, the survey presents a broad conceptual overview of the combination of planning and learning for MDP optimization.
- Open Access
- 11 July 2022
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 5, 908353
A Unifying Framework for Reinforcement Learning and Planning
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization arereinforcement learningandplanning, which both largely have their own research communities. However, if both research fields solve the same problem, then we might be able to disentangle the common factors in their solution approaches. Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning and learning algorithms have to decide. At the end of the paper, we compare a variety of well-known planning, model-free and model-based RL algorithms along these dimensions. Altogether, the framework may help provide deeper insight in the algorithmic design space of planning and reinforcement learning.
- 11 July 2022
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 5, 908353
Open AccessA Unifying Framework for Reinforcement Learning and Planning
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization arereinforcement learningandplanning, which both largely have their own research communities. However, if both research fields solve the same problem, then we might be able to disentangle the common factors in their solution approaches. Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning and learning algorithms have to decide. At the end of the paper, we compare a variety of well-known planning, model-free and model-based RL algorithms along these dimensions. Altogether, the framework may help provide deeper insight in the algorithmic design space of planning and reinforcement learning.