Artificial Intelligence Programming

AI is a scientific tool for solving difficult problems and using it is an excellent opportunity to distinguish your product on the market. In game development, it can be applied for:

  • building a believable computer-controlled player,
  • managing complex in-game economy,
  • generating game content procedurally,
  • learning about player profiles and adapting to their preferences,
  • assessing player activity and processing uploaded content.

We are developing specialised solutions by employing modern techniques in the field of AI. Our team includes excellent programmers and experienced researchers.

Original art by Nikolas Pasternak

Game Theory

Build an intelligent opponent that predicts your actions while taking into account that you anticipate his actions. Sounds insane? Game theory is a branch of science that already solves it. Use it to pursue perfection.

Machine Learning

Take the benefit of data that surrounds us. Process it to find surprising dependencies. Use machine learning to manage large amounts of data, gain information about your users, and learn intelligent behaviours.

Automated Planning

Distribute resources efficiently, build a sustainable economy, and plan effective tactics for your units on the battlefield. No more predefined behaviours. Adapt to a situation and plan your actions automatically.

Computational Intelligence

Life always finds a way. Use nature-inspired methods to overcome any difficult problem by evolving its solution. Computational intelligence is the art of using computer power to achieve goals set by your creativity.

AI Programmer or Scientist – why not both?

Bartłomiej Dzieńkowski

CEO, AI Specialist

Short Bio:

Bartek is our AI specialist and a lead programmer with years of professional experience working on commercial applications, scientific projects, and video games. During the period of his doctoral track, he has developed a novel planning method for video games. He participated in Visiting Researcher Programme organised by Centre for Maritime Research and Experimentation, which is an executive body of NATO’s Science and Technology Organisation. An author of several papers in the field of AI. Currently, Bartek is finalising his doctoral track and focusing on developing AI tools for our customers.

LinkedIn Contact

Responsibilities:

  • consulting AI solutions and providing expertise,
  • designing system architecture and writing the documentation,
  • distributing tasks in the team,
  • implementing core AI algorithms,
  • testing and assuring quality.

Team Skills

Programming Technologies

C# / Unity

99%

C++ / UnrealEngine

80%

Python

99%

Rust

30%

AI Methods and Models

Neural Networks

85%

Genetic Algorithms

80%

Planning and Pathfinding (A*)

99%

Minimax

90%

Published Papers

Employing Game Theory and Computational Intelligence to Find the Optimal Strategy of an Autonomous Underwater Vehicle against a Submarine

Game theory is a tool that may be used to model a player as an intelligent being – one who seeks to optimize his own performance while taking into account the performance of his opponent. However, it is often challenging to apply the theory in practice. In the naval environment, this approach may be used, for instance, to find the best strategy for an Autonomous Underwater Vehicle (AUV) while considering the intelligence of the submarine opponent. Classic approaches based on Minimax suffer from an explosion of states, and they are difficult to use in real-time. The paper introduces an approach that improves the Minimax algorithm in a complex naval environment. It assumes limited and scalable computational resources. The approach takes advantage of a flexible utility function based on a neural network with parameters tuned by a genetic algorithm.

Access Full Text
Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, IEEE (2016)

Dzieńkowski, B., Strode, C., Markowska-Kaczmar, U.: Employing Game Theory and Computational Intelligence to Find the Optimal Strategy of an Autonomous Underwater Vehicle against a Submarine. Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, ACSIS, Vol. 8, pp. 31–40, 2016.

A* Heuristic Based on a Hierarchical Space Model Extracted from Game Replays

The paper presents a new method of building a hierarchical model of the state space. The model is extracted fully automatically from game replays that store executed plan traces. It is used by a novel approach for estimating the distance between states in a state-space graph. The estimate is applied in the A* algorithm as a heuristic function to reduce the search space. The method was validated using the game Smart Blocks. It is a testbed environment for studying methods that benefit from game replay analysis. The proposed heuristic is dedicated to difficult classical planning problems, for which problem-specific or automated heuristics are difficult to obtain.

Access Full Text
Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, IEEE (2016)

Dzieńkowski, B., Markowska-Kaczmar, U.: A* Heuristic Based on a Hierarchical Space Model Extracted from Game Replays. Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, ACSIS, Vol. 8, pp. 21–30, 2016.

Plan and Goal Structure Reconstruction: an Automated and Incremental Method Based on Observation of a Single Agent

Plan reconstruction is a task that appears in plan recognition and learning by practice. The document introduces a method of building a goal graph, which holds a reconstructed plan structure, based on analysis of data provided by the observation of an agent. The approach is STRIPS-free and uses only a little knowledge about an environment. The process is automatic; thus, it does not require manual annotation of observations. The paper provides details of the developed algorithm. In the experimental study, properties of a goal graph were evaluated. Possible application areas of the method are described.

Access Full Text
Proceedings of the Computer Information Systems and Industrial Management: 11th IFIP TC 8 International Conference, Springer (2012)

Dzieńkowski, B., Markowska-Kaczmar, U.: Plan and Goal Structure Reconstruction: an Automated and Incremental Method Based on Observation of a Single Agent. 11th IFIP TC 8 International Conference, CISIM 2012, LNCS, Vol. 7564, pp. 290-301, 2012.

Agent Cooperation within Adversarial Teams in Dynamic Environment - Key Issues and Development Trends

The paper presents a survey of multi-agent systems (MAS) with adversarial teams competing in a dynamic environment. Agents within teams work together against an opposing group of agents to fulfil their contrary goals. The article introduces the specificity of such an environment and indicates fields of cooperation. It emphasises the role of opponent analysis. Popular planning and learning methods are considered. Next, possible fields of practical application are discussed. The final part of the paper presents a summary of applied machine learning methods and points up future development directions.

Access Full Text
Transactions on Computational Collective Intelligence VI, Springer (2012)

Dzieńkowski, B., Markowska-Kaczmar, U.: Agent Cooperation within Adversarial Teams in Dynamic Environment – Key Issues and Development Trends. Transactions on Computational Collective Intelligence VI, LNCS, Vol. 7190, pp. 146-169, 2012.

Analysis of Inter-rater Agreement among Human Observers Who Judge Image Similarity

The paper discusses a problem of inter-rater agreement for the case of human observers who judge how similar pairs of images are. In such a case, significant differences in judgement appear among the group of people. We have observed that for some pairs of images all values of similarity ratings are assigned by various people with approximately the same probability. To investigate this phenomenon in a more thorough manner we performed experiments in which inter-rater coefficients were used to measure the level of agreement for each given pair of images and for each pair of human judges. The results obtained in the experiments suggest that the variation of the level of agreement is considerable among pairs of images as well as among pairs of people.

Access Full Text
Computer Recognition Systems 4, Advances in Intelligent and Soft Computing, Springer (2011)

Michalak, K., Dzieńkowski, B., Hudyma, E., Stanek, M.: Analysis of Inter-rater Agreement among Human Observers Who Judge Image Similarity. Advances in Intelligent and Soft Computing, ISSN 1867-5662, Vol. 95, pp. 249-258, 2011.

Biologically Inspired Agent System Based on Spiking Neural Network

The paper presents the architecture of a biologically inspired agent. The agent’s movement is directly controlled by Spiking Neural Network. The neural network is trained by a genetic algorithm. The agents move in a 3D physical environment. Their primary purpose is to translocate themselves using a virtual body structure and muscles. This approach is inspired by a biological assumption, where the neural network receives signals from sensors and directly controls the muscles.

Access Full Text
Proceedings of the 4th KES International Conference on Agent and Multi-agent Systems: Technologies and Applications, Springer (2010)

Dzieńkowski, B., Markowska-Kaczmar, U.: Biologically Inspired Agent System Based on Spiking Neural Network. Proceedings of the 4th KES International Conference on Agent and Multi-agent Systems: Technologies and Applications, LNCS, Vol. 6071, pp. 110-119, 2010.