Search Results for author: Aske Plaat

Found 53 papers, 18 papers with code

Research Re: search & Re-search

no code implementations20 Mar 2024 Aske Plaat

This study takes a closer look at a depth-first algorithm, AB, and a best-first algorithm, SSS.

A Hybrid Intelligence Method for Argument Mining

no code implementations11 Mar 2024 Michiel van der Meer, Enrico Liscio, Catholijn M. Jonker, Aske Plaat, Piek Vossen, Pradeep K. Murukannaiah

We find that, on the one hand, HyEnA achieves higher coverage and precision than a state-of-the-art automated method when compared to a common set of diverse opinions, justifying the need for human insight.

Argument Mining

Solving Deep Reinforcement Learning Benchmarks with Linear Policy Networks

no code implementations10 Feb 2024 Annie Wong, Jacob de Nobel, Thomas Bäck, Aske Plaat, Anna V. Kononova

Although Deep Reinforcement Learning (DRL) methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex and training times are often long.

Atari Games reinforcement-learning

Explicitly Disentangled Representations in Object-Centric Learning

1 code implementation18 Jan 2024 Riccardo Majellaro, Jonathan Collu, Aske Plaat, Thomas M. Moerland

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning.

Disentanglement Object

EduGym: An Environment and Notebook Suite for Reinforcement Learning Education

1 code implementation17 Nov 2023 Thomas M. Moerland, Matthias Müller-Brockhausen, Zhao Yang, Andrius Bernatavicius, Koen Ponse, Tom Kouwenhoven, Andreas Sauter, Michiel van der Meer, Bram Renting, Aske Plaat

To solve this issue we introduce EduGym, a set of educational reinforcement learning environments and associated interactive notebooks tailored for education.

reinforcement-learning

Subspace Adaptation Prior for Few-Shot Learning

1 code implementation13 Oct 2023 Mike Huisman, Aske Plaat, Jan N. van Rijn

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent.

Few-Shot Image Classification Few-Shot Learning

Understanding Transfer Learning and Gradient-Based Meta-Learning Techniques

1 code implementation9 Oct 2023 Mike Huisman, Aske Plaat, Jan N. van Rijn

Whilst meta-learning techniques have been observed to be successful at this in various scenarios, recent results suggest that when evaluated on tasks from a different data distribution than the one used for training, a baseline that simply finetunes a pre-trained network may be more effective than more complicated meta-learning techniques such as MAML, which is one of the most popular meta-learning techniques.

Meta-Learning Transfer Learning

Fine-grained Affective Processing Capabilities Emerging from Large Language Models

no code implementations4 Sep 2023 Joost Broekens, Bernhard Hilpert, Suzan Verberne, Kim Baraka, Patrick Gebhard, Aske Plaat

Large language models, in particular generative pre-trained transformers (GPTs), show impressive results on a wide variety of language-related tasks.

Sentiment Analysis

Two-Memory Reinforcement Learning

no code implementations20 Apr 2023 Zhao Yang, Thomas. M. Moerland, Mike Preuss, Aske Plaat

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 parametric neural networks.

reinforcement-learning Representation Learning +1

First Go, then Post-Explore: the Benefits of Post-Exploration in Intrinsic Motivation

no code implementations6 Dec 2022 Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat

In this paper, we present a clear ablation study of post-exploration in a general intrinsically motivated goal exploration process (IMGEP) framework, that the Go-Explore paper did not show.

Continuous Control Reinforcement Learning (RL)

Continuous Episodic Control

no code implementations28 Nov 2022 Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat

Therefore, this paper introduces Continuous Episodic Control (CEC), a novel non-parametric episodic memory algorithm for sequential decision making in problems with a continuous action space.

Continuous Control Decision Making +2

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation

no code implementations29 Mar 2022 Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat

Go-Explore achieved breakthrough performance on challenging reinforcement learning (RL) tasks with sparse rewards.

Reinforcement Learning (RL)

On Credit Assignment in Hierarchical Reinforcement Learning

1 code implementation7 Mar 2022 Joery A. de Vries, Thomas M. Moerland, Aske Plaat

To improve our fundamental understanding of HRL, we investigate hierarchical credit assignment from the perspective of conventional multistep reinforcement learning.

Hierarchical Reinforcement Learning reinforcement-learning +1

Reliable validation of Reinforcement Learning Benchmarks

no code implementations2 Mar 2022 Matthias Müller-Brockhausen, Aske Plaat, Mike Preuss

Reinforcement Learning (RL) is one of the most dynamic research areas in Game AI and AI as a whole, and a wide variety of games are used as its prominent test problems.

Benchmarking Data Compression +3

Deep Reinforcement Learning, a textbook

no code implementations4 Jan 2022 Aske Plaat

The aim of this book is to provide a comprehensive overview of the field of deep reinforcement learning.

Autonomous Driving Hierarchical Reinforcement Learning +5

Potential-based Reward Shaping in Sokoban

no code implementations10 Sep 2021 Zhao Yang, Mike Preuss, Aske Plaat

While previous work has investigated the use of expert knowledge to generate potential functions, in this work, we study whether we can use a search algorithm(A*) to automatically generate a potential function for reward shaping in Sokoban, a well-known planning task.

Transfer Learning and Curriculum Learning in Sokoban

no code implementations25 May 2021 Zhao Yang, Mike Preuss, Aske Plaat

In reinforcement learning, learning actions for a behavior policy that can be applied to new environments is still a challenge, especially for tasks that involve much planning.

reinforcement-learning Reinforcement Learning (RL) +1

Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning

no code implementations13 May 2021 Hui Wang, Mike Preuss, Aske Plaat

AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play.

Board Games reinforcement-learning +1

Stateless Neural Meta-Learning using Second-Order Gradients

1 code implementation21 Apr 2021 Mike Huisman, Aske Plaat, Jan N. van Rijn

Deep learning typically requires large data sets and much compute power for each new problem that is learned.

Image Classification Meta-Learning

Visualizing MuZero Models

1 code implementation ICML Workshop URL 2021 Joery A. de Vries, Ken S. Voskuil, Thomas M. Moerland, Aske Plaat

In contrast to standard forward dynamics models that predict a full next state, value equivalent models are trained to predict a future value, thereby emphasizing value relevant information in the representations.

Game of Go Model-based Reinforcement Learning

Multiple Node Immunisation for Preventing Epidemics on Networks by Exact Multiobjective Optimisation of Cost and Shield-Value

1 code implementation13 Oct 2020 Michael Emmerich, Joost Nibbeling, Marios Kefalas, Aske Plaat

The general problem in this paper is vertex (node) subset selection with the goal to contain an infection that spreads in a network.

A Survey of Deep Meta-Learning

no code implementations7 Oct 2020 Mike Huisman, Jan N. van Rijn, Aske Plaat

Meta-learning is one approach to address this issue, by enabling the network to learn how to learn.

Meta-Learning

A Unifying Framework for Reinforcement Learning and Planning

no code implementations26 Jun 2020 Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker

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.

Decision Making reinforcement-learning +1

Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning

no code implementations14 Jun 2020 Hui Wang, Mike Preuss, Michael Emmerich, Aske Plaat

A later algorithm, Nested Rollout Policy Adaptation, was able to find a new record of 82 steps, albeit with large computational resources.

Game of Go reinforcement-learning +3

The Second Type of Uncertainty in Monte Carlo Tree Search

1 code implementation19 May 2020 Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker

Monte Carlo Tree Search (MCTS) efficiently balances exploration and exploitation in tree search based on count-derived uncertainty.

Vocal Bursts Type Prediction

Warm-Start AlphaZero Self-Play Search Enhancements

no code implementations26 Apr 2020 Hui Wang, Mike Preuss, Aske Plaat

Recently, AlphaZero has achieved landmark results in deep reinforcement learning, by providing a single self-play architecture that learned three different games at super human level.

Board Games Evolutionary Algorithms

A New Challenge: Approaching Tetris Link with AI

no code implementations1 Apr 2020 Matthias Muller-Brockhausen, Mike Preuss, Aske Plaat

This paper focuses on a new game, Tetris Link, a board game that is still lacking any scientific analysis.

Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?

no code implementations12 Mar 2020 Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat

A secondary result of our experiments concerns the choice of optimization goals, for which we also provide recommendations.

Hyper-Parameter Sweep on AlphaZero General

1 code implementation19 Mar 2019 Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat

Therefore, in this paper, we choose 12 parameters in AlphaZero and evaluate how these parameters contribute to training.

Game of Go

Assessing the Potential of Classical Q-learning in General Game Playing

1 code implementation14 Oct 2018 Hui Wang, Michael Emmerich, Aske Plaat

For small games, simple classical table-based Q-learning might still be the algorithm of choice.

Board Games Q-Learning +2

A0C: Alpha Zero in Continuous Action Space

2 code implementations24 May 2018 Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker

A core novelty of Alpha Zero is the interleaving of tree search and deep learning, which has proven very successful in board games like Chess, Shogi and Go.

Board Games reinforcement-learning +2

Monte Carlo Tree Search for Asymmetric Trees

2 code implementations23 May 2018 Thomas M. Moerland, Joost Broekens, Aske Plaat, Catholijn M. Jonker

Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account.

Atari Games OpenAI Gym

Bringing Fault-Tolerant GigaHertz-Computing to Space: A Multi-Stage Software-Side Fault-Tolerance Approach for Miniaturized Spacecraft

1 code implementation23 Aug 2017 Christian M. Fuchs, Todor Stefanov, Nadia Murillo, Aske Plaat

Modern embedded technology is a driving factor in satellite miniaturization, contributing to a massive boom in satellite launches and a rapidly evolving new space industry.

Distributed, Parallel, and Cluster Computing Operating Systems

A Minimax Algorithm Better Than Alpha-beta?: No and Yes

no code implementations11 Feb 2017 Aske Plaat, Jonathan Schaeffer, Wim Pijls, Arie de Bruin

The crucial step is the realization that transposition tables contain so-called solution trees, structures that are used in best-first search algorithms like SSS*.

Ensemble UCT Needs High Exploitation

no code implementations28 Sep 2015 S. Ali Mirsoleimani, Aske Plaat, Jaap van den Herik

Small search trees occur in variations of MCTS, such as parallel and ensemble approaches.

Vocal Bursts Intensity Prediction

Best-First and Depth-First Minimax Search in Practice

no code implementations7 May 2015 Aske Plaat, Jonathan Schaeffer, Wim Pijls, Arie de Bruin

Most practitioners use a variant of the Alpha-Beta algorithm, a simple depth-first pro- cedure, for searching minimax trees.

Data Science and Ebola

no code implementations11 Apr 2015 Aske Plaat

In every discipline, large, diverse, and rich data sets are emerging, from astrophysics, to the life sciences, to the behavioral sciences, to finance and commerce, to the humanities and to the arts.

Why Local Search Excels in Expression Simplification

no code implementations18 Sep 2014 Ben Ruijl, Aske Plaat, Jos Vermaseren, Jaap van den Herik

For High Energy Physics this means that numerical integrations that took weeks can now be done in hours.

Numerical Integration

HEPGAME and the Simplification of Expressions

no code implementations25 May 2014 Ben Ruijl, Jos Vermaseren, Aske Plaat, Jaap van den Herik

We observe that a variable $C_p$ solves our domain: it yields more exploration at the bottom and as a result the tuning problem has been simplified.

Numerical Integration

MTD(f), A Minimax Algorithm Faster Than NegaScout

no code implementations5 Apr 2014 Aske Plaat

MTD(f) is a new minimax search algorithm, simpler and more efficient than previous algorithms.

Nearly Optimal Minimax Tree Search?

no code implementations5 Apr 2014 Aske Plaat, Jonathan Schaeffer, Wim Pijls, Arie de Bruin

Empirical evidence shows that in all three games, enhanced Alpha-Beta search is capable of building a tree that is close in size to that of the minimal graph.

A New Paradigm for Minimax Search

1 code implementation5 Apr 2014 Aske Plaat, Jonathan Schaeffer, Wim Pijls, Arie de Bruin

This paper introduces a new paradigm for minimax game-tree search algo- rithms.

SSS* = Alpha-Beta + TT

no code implementations5 Apr 2014 Aske Plaat, Jonathan Schaeffer, Wim Pijls, Arie de Bruin

AB-SSS* is comparable in performance to Alpha-Beta on leaf node count in all three games, making it a viable alternative to Alpha-Beta in practise.

Combining Simulated Annealing and Monte Carlo Tree Search for Expression Simplification

no code implementations3 Dec 2013 Ben Ruijl, Jos Vermaseren, Aske Plaat, Jaap van den Herik

Yet, this approach is fit for further improvements since it is sensitive to the so-called exploration-exploitation constant $C_p$ and the number of tree updates $N$.

Cannot find the paper you are looking for? You can Submit a new open access paper.