Wojciech Jaśkowski
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
Wojciech Jaśkowski has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Krzysztof Krawiec
Poznan University of Technology
19 shared publications - Bartosz Wieloch
Poznań University of Technology, Poznań, Poland
9 shared publications Marcin Szubert
Poznan University of Technology
6 shared publications- Marcin Szubert
Poznan University of Technology
4 shared publications Krzysztof Krawiec
Poznań University of Technology, Poznań, Poland
3 shared publicationsPaweł Liskowski
Poznan University of Technology
3 shared publications
Latest Publications
- Open Access
How to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the gradient of the critic with respect to input actions. However, instead of gradients, the critic is, typically, only trained to accurately predict expected returns, which, on their own, are useless for policy optimization. In this paper, we propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients, which explicitly learns the action-value gradient. MAGE backpropagates through the learned dynamics to compute gradient targets in temporal difference learning, leading to a critic tailored for policy improvement. On a set of MuJoCo continuous-control tasks, we demonstrate the efficiency of the algorithm in comparison to model-free and model-based state-of-the-art baselines.
Open AccessHow to Learn a Useful Critic? Model-based Action-Gradient-Estimator Policy Optimization
Deterministic-policy actor-critic algorithms for continuous control improve the actor by plugging its actions into the critic and ascending the action-value gradient, which is obtained by chaining the actor's Jacobian matrix with the gradient of the critic with respect to input actions. However, instead of gradients, the critic is, typically, only trained to accurately predict expected returns, which, on their own, are useless for policy optimization. In this paper, we propose MAGE, a model-based actor-critic algorithm, grounded in the theory of policy gradients, which explicitly learns the action-value gradient. MAGE backpropagates through the learned dynamics to compute gradient targets in temporal difference learning, leading to a critic tailored for policy improvement. On a set of MuJoCo continuous-control tasks, we demonstrate the efficiency of the algorithm in comparison to model-free and model-based state-of-the-art baselines.
- 19 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 11 (3) , 248-259
ViZDoom Competitions: Playing Doom From Pixels
This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors. Bestperforming agents are described in more detail. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom.
- 19 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 11 (3) , 248-259
ViZDoom Competitions: Playing Doom From Pixels
This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors. Bestperforming agents are described in more detail. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom.
- Open Access
- 11 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (1) , 3-14
Mastering 2048 With Delayed Temporal Coherence Learning, Multistage Weight Promotion, Redundant Encoding, and Carousel Shaping
2048 is an engaging single-player nondeterministic video puzzle game, which, thanks to the simple rules and hard-tomaster gameplay, has gained massive popularity in recent years. As 2048 can be conveniently embedded into the discrete-state Markov decision processes framework, we treat it as a testbed for evaluating existing and new methods in reinforcement learning. With the aim to develop a strong 2048 playing program, we employ temporal difference learning with systematic n-tuple networks. We show that this basic method can be significantly improved with temporal coherence learning, multistage function approximator with weight promotion, carousel shaping, and redundant encoding. In addition, we demonstrate how to take advantage of the characteristics of the n-tuple network, to improve the algorithmic effectiveness of the learning process by delaying the (decayed) update and applying lock-free optimistic parallelism to effortlessly make advantage of multiple CPU cores. This way, we were able to develop the best known 2048 playing program to date, which confirms the effectiveness of the introduced methods for discrete-state Markov decision problems.
- 11 January 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 10 (1) , 3-14
Open AccessMastering 2048 With Delayed Temporal Coherence Learning, Multistage Weight Promotion, Redundant Encoding, and Carousel Shaping
2048 is an engaging single-player nondeterministic video puzzle game, which, thanks to the simple rules and hard-tomaster gameplay, has gained massive popularity in recent years. As 2048 can be conveniently embedded into the discrete-state Markov decision processes framework, we treat it as a testbed for evaluating existing and new methods in reinforcement learning. With the aim to develop a strong 2048 playing program, we employ temporal difference learning with systematic n-tuple networks. We show that this basic method can be significantly improved with temporal coherence learning, multistage function approximator with weight promotion, carousel shaping, and redundant encoding. In addition, we demonstrate how to take advantage of the characteristics of the n-tuple network, to improve the algorithmic effectiveness of the learning process by delaying the (decayed) update and applying lock-free optimistic parallelism to effortlessly make advantage of multiple CPU cores. This way, we were able to develop the best known 2048 playing program to date, which confirms the effectiveness of the introduced methods for discrete-state Markov decision problems.
- Open Access
Mastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping
2048 is an engaging single-player, nondeterministic video puzzle game, which, thanks to the simple rules and hard-to-master gameplay, has gained massive popularity in recent years. As 2048 can be conveniently embedded into the discrete-state Markov decision processes framework, we treat it as a testbed for evaluating existing and new methods in reinforcement learning. With the aim to develop a strong 2048 playing program, we employ temporal difference learning with systematic n-tuple networks. We show that this basic method can be significantly improved with temporal coherence learning, multi-stage function approximator with weight promotion, carousel shaping, and redundant encoding. In addition, we demonstrate how to take advantage of the characteristics of the n-tuple network, to improve the algorithmic effectiveness of the learning process by i) delaying the (decayed) update and applying lock-free optimistic parallelism to effortlessly make advantage of multiple CPU cores. This way, we were able to develop the best known 2048 playing program to date, which confirms the effectiveness of the introduced methods for discrete-state Markov decision problems.
Open AccessMastering 2048 with Delayed Temporal Coherence Learning, Multi-Stage Weight Promotion, Redundant Encoding and Carousel Shaping
2048 is an engaging single-player, nondeterministic video puzzle game, which, thanks to the simple rules and hard-to-master gameplay, has gained massive popularity in recent years. As 2048 can be conveniently embedded into the discrete-state Markov decision processes framework, we treat it as a testbed for evaluating existing and new methods in reinforcement learning. With the aim to develop a strong 2048 playing program, we employ temporal difference learning with systematic n-tuple networks. We show that this basic method can be significantly improved with temporal coherence learning, multi-stage function approximator with weight promotion, carousel shaping, and redundant encoding. In addition, we demonstrate how to take advantage of the characteristics of the n-tuple network, to improve the algorithmic effectiveness of the learning process by i) delaying the (decayed) update and applying lock-free optimistic parallelism to effortlessly make advantage of multiple CPU cores. This way, we were able to develop the best known 2048 playing program to date, which confirms the effectiveness of the introduced methods for discrete-state Markov decision problems.
- Open Access
ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning
The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game using the screen buffer. ViZDoom is lightweight, fast, and highly customizable via a convenient mechanism of user scenarios. In the experimental part, we test the environment by trying to learn bots for two scenarios: a basic move-and-shoot task and a more complex maze-navigation problem. Using convolutional deep neural networks with Q-learning and experience replay, for both scenarios, we were able to train competent bots, which exhibit human-like behaviors. The results confirm the utility of ViZDoom as an AI research platform and imply that visual reinforcement learning in 3D realistic first-person perspective environments is feasible.
Open AccessViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning
The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 games, however, do not resemble real-world tasks since they involve non-realistic 2D environments and the third-person perspective. Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world. The software, called ViZDoom, is based on the classical first-person shooter video game, Doom. It allows developing bots that play the game using the screen buffer. ViZDoom is lightweight, fast, and highly customizable via a convenient mechanism of user scenarios. In the experimental part, we test the environment by trying to learn bots for two scenarios: a basic move-and-shoot task and a more complex maze-navigation problem. Using convolutional deep neural networks with Q-learning and experience replay, for both scenarios, we were able to train competent bots, which exhibit human-like behaviors. The results confirm the utility of ViZDoom as an AI research platform and imply that visual reinforcement learning in 3D realistic first-person perspective environments is feasible.
- Open Access
- 1 March 2016
- Published by University of Zielona Góra, Poland in International Journal of Applied Mathematics and Computer Science
- Vol. 26 (1) , 215-229
The performance profile: A multi–criteria performance evaluation method for test–based problems
In test-based problems, solutions produced by search algorithms are typically assessed using average outcomes of interactions with multiple tests. This aggregation leads to information loss, which can render different solutions apparently indifferent and hinder comparison of search algorithms. In this paper we introduce the performance profile, a generic, domain-independent, multi-criteria performance evaluation method that mitigates this problem by characterizing the performance of a solution by a vector of outcomes of interactions with tests of various difficulty. To demonstrate the usefulness of this gauge, we employ it to analyze the behavior of Othello and Iterated Prisoner’s Dilemma players produced by five (co)evolutionary algorithms as well as players known from previous publications. Performance profiles reveal interesting differences between the players, which escape the attention of the scalar performance measure of the expected utility. In particular, they allow us to observe that evolution with random sampling produces players coping well against the mediocre opponents, while the coevolutionary and temporal difference learning strategies play better against the high-grade opponents. We postulate that performance profiles improve our understanding of characteristics of search algorithms applied to arbitrary test-based problems, and can prospectively help design better methods for interactive domains.
- 1 March 2016
- Published by University of Zielona Góra, Poland in International Journal of Applied Mathematics and Computer Science
- Vol. 26 (1) , 215-229
Open AccessThe performance profile: A multi–criteria performance evaluation method for test–based problems
In test-based problems, solutions produced by search algorithms are typically assessed using average outcomes of interactions with multiple tests. This aggregation leads to information loss, which can render different solutions apparently indifferent and hinder comparison of search algorithms. In this paper we introduce the performance profile, a generic, domain-independent, multi-criteria performance evaluation method that mitigates this problem by characterizing the performance of a solution by a vector of outcomes of interactions with tests of various difficulty. To demonstrate the usefulness of this gauge, we employ it to analyze the behavior of Othello and Iterated Prisoner’s Dilemma players produced by five (co)evolutionary algorithms as well as players known from previous publications. Performance profiles reveal interesting differences between the players, which escape the attention of the scalar performance measure of the expected utility. In particular, they allow us to observe that evolution with random sampling produces players coping well against the mediocre opponents, while the coevolutionary and temporal difference learning strategies play better against the high-grade opponents. We postulate that performance profiles improve our understanding of characteristics of search algorithms applied to arbitrary test-based problems, and can prospectively help design better methods for interactive domains.
- 17 March 2015
- Published by Springer Nature
- p. 394-405
The Role of Behavioral Diversity and Difficulty of Opponents in Coevolving Game-Playing Agents
- 17 March 2015
- Published by Springer Nature
- p. 394-405
The Role of Behavioral Diversity and Difficulty of Opponents in Coevolving Game-Playing Agents
- Open Access
- 14 January 2015
- Published by Springer Nature in Annals of Operations Research
- Vol. 242 (1) , 33-62
A hybrid MIP-based large neighborhood search heuristic for solving the machine reassignment problem
- 14 January 2015
- Published by Springer Nature in Annals of Operations Research
- Vol. 242 (1) , 33-62
Open AccessA hybrid MIP-based large neighborhood search heuristic for solving the machine reassignment problem
- 29 November 2014
- Published by Springer Nature
- p. 301-312
Multi-Criteria Comparison of Coevolution and Temporal Difference Learning on Othello
- 29 November 2014
- Published by Springer Nature
- p. 301-312
Multi-Criteria Comparison of Coevolution and Temporal Difference Learning on Othello