Maciej Świechowski
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
Maciej Świechowski has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Jacek Mańdziuk
Warsaw University of Technology
16 shared publications Tomasz Tajmajer
Institute of Informatics University of Warsaw, Poland and
3 shared publicationsAndrzej Janusz
Institute of Informatics, University of Warsaw, Warsaw, Poland
2 shared publications- Andrzej Janusz
Queensland University of Technology
2 shared publications - Bartosz Sawicki
Warsaw University of Technology
2 shared publications - Konrad Godlewski
Warsaw University of Technology, Warsaw, Poland
2 shared publications
Latest Publications
- Open Access
- 1 May 2026
- Published by Elsevier in SSRN Electronic Journal
Data Augmentation in Computer Vision: A Comprehensive Survey
Data augmentation (DA) has become one of the most effective strategies for obtaining large training datasets, enhancing model efficiency, improving generalization, and reducing biases caused by incomplete data. It is particularly important in computer vision (CV), where vast amounts of data are required and where most state-of-the-art approaches are based on deep learning. In this work, we present a comprehensive review of augmentation techniques in CV, including various transformations (perturbing existing data) and synthesis (generating new samples). We propose a well-structured taxonomy that covers both traditional methods and emerging trends. In terms of temporal scope, we aim to cover the most important DA methods for CV, from early applications in 1990 up to the year 2025. CV is a broad field, however, nearly all of the reviewed papers focus on image or video processing. We discuss multi-domain techniques as well as those designed for contextspecific modalities and applications, e.g., medical, underwater, or infrared imaging. Current and future challenges are addressed, and we also review available programming tools for practitioners.
- 1 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessData Augmentation in Computer Vision: A Comprehensive Survey
Data augmentation (DA) has become one of the most effective strategies for obtaining large training datasets, enhancing model efficiency, improving generalization, and reducing biases caused by incomplete data. It is particularly important in computer vision (CV), where vast amounts of data are required and where most state-of-the-art approaches are based on deep learning. In this work, we present a comprehensive review of augmentation techniques in CV, including various transformations (perturbing existing data) and synthesis (generating new samples). We propose a well-structured taxonomy that covers both traditional methods and emerging trends. In terms of temporal scope, we aim to cover the most important DA methods for CV, from early applications in 1990 up to the year 2025. CV is a broad field, however, nearly all of the reviewed papers focus on image or video processing. We discuss multi-domain techniques as well as those designed for contextspecific modalities and applications, e.g., medical, underwater, or infrared imaging. Current and future challenges are addressed, and we also review available programming tools for practitioners.
- 5 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (4) , 954-964
AutoGT: Automatic Generation of Game Trees for Algorithm Benchmarking
Game tree search algorithms play a vital role in application of computational and artificial intelligence methods in games and sequential combinatorial optimization problems. This paper addresses the need for robust and comprehensive benchmarking of these algorithms through the procedural generation of benchmarks. We introduce a novel game tree generator AutoGT built upon the idea of top-down propagation of various game parameters. Thanks to its extensive parameterization, AutoGT enables researchers to evaluate their methods on virtually unlimited number of unique benchmarks. To demonstrate the efficacy and usefulness of the generator, we present comparative results of several standard game-playing algorithms: a game theory optimal player (GTO), a player making moves according to a uniform random distribution, and a few variants of Monte Carlo Tree Search (MCTS) based players. Our findings indicate that for a given set of benchmark parameters, the results are repeatable with low deviation. However, when testing across various parameter settings, the performance becomes more diverse, allowing for a broader and more detailed assessment of the algorithms. The paper includes a link to the full code of AutoGT benchmark generation method.
- 5 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (4) , 954-964
AutoGT: Automatic Generation of Game Trees for Algorithm Benchmarking
Game tree search algorithms play a vital role in application of computational and artificial intelligence methods in games and sequential combinatorial optimization problems. This paper addresses the need for robust and comprehensive benchmarking of these algorithms through the procedural generation of benchmarks. We introduce a novel game tree generator AutoGT built upon the idea of top-down propagation of various game parameters. Thanks to its extensive parameterization, AutoGT enables researchers to evaluate their methods on virtually unlimited number of unique benchmarks. To demonstrate the efficacy and usefulness of the generator, we present comparative results of several standard game-playing algorithms: a game theory optimal player (GTO), a player making moves according to a uniform random distribution, and a few variants of Monte Carlo Tree Search (MCTS) based players. Our findings indicate that for a given set of benchmark parameters, the results are repeatable with low deviation. However, when testing across various parameter settings, the performance becomes more diverse, allowing for a broader and more detailed assessment of the algorithms. The paper includes a link to the full code of AutoGT benchmark generation method.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (4) , 912-922
Combining Tree Search With Value Prediction Models Capable of Estimating Their Uncertainty
The aim of this paper is twofold. Firstly, we propose a method that combines tree search – specifically, Monte Carlo Tree Search – with value prediction models conditionally based on the model's uncertainty in a given state. If, during the search, this uncertainty is within the allowed margin, the current path is terminated, thereby saving simulation budget. This method, overlooked in literature, results in a non-uniform frequency of model usage, in contrast to typical methods applied to game-playing agents, which we summarize in the paper. Secondly, we investigate the effects of using models with various frequencies and prediction accuracies. Rich empirical results demonstrate the impact of 110 combinations of these parameters across various search budget scenarios. Generally, weaker players, for example, those performing fewer search iterations per move, benefit more from a broad selection of prediction models. For stronger baseline MCTS players, the model should only be used when its predictions achieve an accuracy greater than 0.9, especially when the objective is to develop an agent with high efficacy. Practical applicability of the proposed approach has been demonstrated in additional experiments involving chess and Othello, employing different approaches to prediction models. In both of them, it outperformed the baseline approaches.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (4) , 912-922
Combining Tree Search With Value Prediction Models Capable of Estimating Their Uncertainty
The aim of this paper is twofold. Firstly, we propose a method that combines tree search – specifically, Monte Carlo Tree Search – with value prediction models conditionally based on the model's uncertainty in a given state. If, during the search, this uncertainty is within the allowed margin, the current path is terminated, thereby saving simulation budget. This method, overlooked in literature, results in a non-uniform frequency of model usage, in contrast to typical methods applied to game-playing agents, which we summarize in the paper. Secondly, we investigate the effects of using models with various frequencies and prediction accuracies. Rich empirical results demonstrate the impact of 110 combinations of these parameters across various search budget scenarios. Generally, weaker players, for example, those performing fewer search iterations per move, benefit more from a broad selection of prediction models. For stronger baseline MCTS players, the model should only be used when its predictions achieve an accuracy greater than 0.9, especially when the objective is to develop an agent with high efficacy. Practical applicability of the proposed approach has been demonstrated in additional experiments involving chess and Othello, employing different approaches to prediction models. In both of them, it outperformed the baseline approaches.
- 30 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Fuzzy Utility AI for Handling Uncertainty in Video Game Bots Implementation
Utility AI is an effective tool used to design the behavior of AI agents in games and other multi-agent settings. Lately, it has been gaining a lot of attention in the video games domain, whereby computer players have to act quickly and maintain balance between the effectiveness (i.e., being strong) and the narrative goals (i.e., fulfilling a particular role). This paper presents a novel extension of Utility AI called Fuzzy Utility AI for game environments with uncertain and incomplete information. The main introduced ideas are fuzzy considerations, that generalize the standard considerations in Utility AI, and a new, uncertainty-aware, formula of calculating the utility score. Our intention was to compare the baseline approach with Fuzzy Utility AI using a rudimentary example (a testbed) that is simple to follow and also isolates all external factors that could influence the performance. The empirical results - with a dataset included - show that Fuzzy Utility AI is a more effective approach in environments with incomplete information that needs to be predicted with uncertainty. In the paper, we further confirm the empirical findings with a theoretical analysis.
- 30 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Fuzzy Utility AI for Handling Uncertainty in Video Game Bots Implementation
Utility AI is an effective tool used to design the behavior of AI agents in games and other multi-agent settings. Lately, it has been gaining a lot of attention in the video games domain, whereby computer players have to act quickly and maintain balance between the effectiveness (i.e., being strong) and the narrative goals (i.e., fulfilling a particular role). This paper presents a novel extension of Utility AI called Fuzzy Utility AI for game environments with uncertain and incomplete information. The main introduced ideas are fuzzy considerations, that generalize the standard considerations in Utility AI, and a new, uncertainty-aware, formula of calculating the utility score. Our intention was to compare the baseline approach with Fuzzy Utility AI using a rudimentary example (a testbed) that is simple to follow and also isolates all external factors that could influence the performance. The empirical results - with a dataset included - show that Fuzzy Utility AI is a more effective approach in environments with incomplete information that needs to be predicted with uncertainty. In the paper, we further confirm the empirical findings with a theoretical analysis.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (4) , 5303-5311
Don’t Predict Counterfactual Values, Predict Expected Values Instead
Counterfactual Regret Minimization algorithms are the most popular way of estimating the Nash Equilibrium in imperfect-information zero-sum games. In particular, DeepStack -- the state-of-the-art Poker bot -- employs the so-called Deep Counterfactual Value Network (DCVN) to learn the Counterfactual Values (CFVs) associated with various states in the game. Each CFV is a multiplication of two factors: (1) the probability that the opponent would reach a given state in a game, which can be explicitly calculated from the input data, and (2) the expected value (EV) of a payoff in that state, which is a complex function of the input data, hard to calculate. In this paper, we propose a simple yet powerful modification to the CFVs estimation process, which consists in utilizing a deep neural network to estimate only the EV factor of CFV. This new target setting significantly simplifies the learning problem and leads to much more accurate CFVs estimation. A direct comparison, in terms of CFVs prediction losses, shows a significant prediction accuracy improvement of the proposed approach (DEVN) over the original DCVN formulation (relatively by 9.18-15.70% when using card abstraction, and by 3.37-8.39% without card abstraction, depending on a particular setting). Furthermore, the application of DEVN improves the theoretical lower bound of the error by 29.05-31.83% compared to the DCVN pipeline when card abstraction is applied. Additionally, DEVN is able to achieve the goal using significantly smaller, and faster to infer, networks. While the proposed modification may seem to be of a rather technical nature, it, in fact, presents a fundamentally different approach to the overall process of learning and estimating CFVs, since the distributions of the training signals differ significantly between DCVN and DEVN. The former estimates CFVs, which are biased by the probability of reaching a given game state, while training the latter relies on a direct EV estimation, regardless of the state probability. In effect, the learning signal of DEVN presents a better estimation of the true value of a given state, thus allowing more accurate CFVs estimation.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (4) , 5303-5311
Open AccessDon’t Predict Counterfactual Values, Predict Expected Values Instead
Counterfactual Regret Minimization algorithms are the most popular way of estimating the Nash Equilibrium in imperfect-information zero-sum games. In particular, DeepStack -- the state-of-the-art Poker bot -- employs the so-called Deep Counterfactual Value Network (DCVN) to learn the Counterfactual Values (CFVs) associated with various states in the game. Each CFV is a multiplication of two factors: (1) the probability that the opponent would reach a given state in a game, which can be explicitly calculated from the input data, and (2) the expected value (EV) of a payoff in that state, which is a complex function of the input data, hard to calculate. In this paper, we propose a simple yet powerful modification to the CFVs estimation process, which consists in utilizing a deep neural network to estimate only the EV factor of CFV. This new target setting significantly simplifies the learning problem and leads to much more accurate CFVs estimation. A direct comparison, in terms of CFVs prediction losses, shows a significant prediction accuracy improvement of the proposed approach (DEVN) over the original DCVN formulation (relatively by 9.18-15.70% when using card abstraction, and by 3.37-8.39% without card abstraction, depending on a particular setting). Furthermore, the application of DEVN improves the theoretical lower bound of the error by 29.05-31.83% compared to the DCVN pipeline when card abstraction is applied. Additionally, DEVN is able to achieve the goal using significantly smaller, and faster to infer, networks. While the proposed modification may seem to be of a rather technical nature, it, in fact, presents a fundamentally different approach to the overall process of learning and estimating CFVs, since the distributions of the training signals differ significantly between DCVN and DEVN. The former estimates CFVs, which are biased by the probability of reaching a given game state, while training the latter relies on a direct EV estimation, regardless of the state probability. In effect, the learning signal of DEVN presents a better estimation of the true value of a given state, thus allowing more accurate CFVs estimation.
- Top Cited PapersOpen Access
- 19 July 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (3) , 2497-2562
Monte Carlo Tree Search: a review of recent modifications and applications
Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random sampling in the form of simulations and stores statistics of actions to make more educated choices in each subsequent iteration. The method has become a state-of-the-art technique for combinatorial games. However, in more complex games (e.g. those with a high branching factor or real-time ones) as well as in various practical domains (e.g. transportation, scheduling or security) an efficient MCTS application often requires its problem-dependent modification or integration with other techniques. Such domain-specific modifications and hybrid approaches are the main focus of this survey. The last major MCTS survey was published in 2012. Contributions that appeared since its release are of particular interest for this review.
- 19 July 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (3) , 2497-2562
Top Cited PapersOpen AccessMonte Carlo Tree Search: a review of recent modifications and applications
Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random sampling in the form of simulations and stores statistics of actions to make more educated choices in each subsequent iteration. The method has become a state-of-the-art technique for combinatorial games. However, in more complex games (e.g. those with a high branching factor or real-time ones) as well as in various practical domains (e.g. transportation, scheduling or security) an efficient MCTS application often requires its problem-dependent modification or integration with other techniques. Such domain-specific modifications and hybrid approaches are the main focus of this survey. The last major MCTS survey was published in 2012. Contributions that appeared since its release are of particular interest for this review.
- 4 July 2022
- Published by Springer Nature
- p. 44-53
Prescriptive Analytics for Optimization of FMCG Delivery Plans
- 4 July 2022
- Published by Springer Nature
- p. 44-53
Prescriptive Analytics for Optimization of FMCG Delivery Plans
- Open Access
Monte Carlo Tree Search: A Review of Recent Modifications and Applications
Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random sampling in the form of simulations and stores statistics of actions to make more educated choices in each subsequent iteration. The method has become a state-of-the-art technique for combinatorial games, however, in more complex games (e.g. those with high branching factor or real-time ones), as well as in various practical domains (e.g. transportation, scheduling or security) an efficient MCTS application often requires its problem-dependent modification or integration with other techniques. Such domain-specific modifications and hybrid approaches are the main focus of this survey. The last major MCTS survey has been published in 2012. Contributions that appeared since its release are of particular interest for this review.
Open AccessMonte Carlo Tree Search: A Review of Recent Modifications and Applications
Monte Carlo Tree Search (MCTS) is a powerful approach to designing game-playing bots or solving sequential decision problems. The method relies on intelligent tree search that balances exploration and exploitation. MCTS performs random sampling in the form of simulations and stores statistics of actions to make more educated choices in each subsequent iteration. The method has become a state-of-the-art technique for combinatorial games, however, in more complex games (e.g. those with high branching factor or real-time ones), as well as in various practical domains (e.g. transportation, scheduling or security) an efficient MCTS application often requires its problem-dependent modification or integration with other techniques. Such domain-specific modifications and hybrid approaches are the main focus of this survey. The last major MCTS survey has been published in 2012. Contributions that appeared since its release are of particular interest for this review.
- Open Access
Deep Learning and Artificial General Intelligence: Still a Long Way to Go
In recent years, deep learning using neural network architecture, i.e. deep neural networks, has been on the frontier of computer science research. It has even lead to superhuman performance in some problems, e.g., in computer vision, games and biology, and as a result the term deep learning revolution was coined. The undisputed success and rapid growth of deep learning suggests that, in future, it might become an enabler for Artificial General Intelligence (AGI). In this article, we approach this statement critically showing five major reasons of why deep neural networks, as of the current state, are not ready to be the technique of choice for reaching AGI.
Open AccessDeep Learning and Artificial General Intelligence: Still a Long Way to Go
In recent years, deep learning using neural network architecture, i.e. deep neural networks, has been on the frontier of computer science research. It has even lead to superhuman performance in some problems, e.g., in computer vision, games and biology, and as a result the term deep learning revolution was coined. The undisputed success and rapid growth of deep learning suggests that, in future, it might become an enabler for Artificial General Intelligence (AGI). In this article, we approach this statement critically showing five major reasons of why deep neural networks, as of the current state, are not ready to be the technique of choice for reaching AGI.
- Open Access
- 26 September 2021
- Published by Polish Information Processing Society PTI in Annals of Computer Science and Information Systems
- Vol. 25, 101-110
A Practical Solution to Handling Randomness and Imperfect Information in Monte Carlo Tree Search
- 26 September 2021
- Published by Polish Information Processing Society PTI in Annals of Computer Science and Information Systems
- Vol. 25, 101-110
Open AccessA Practical Solution to Handling Randomness and Imperfect Information in Monte Carlo Tree Search