Dynamic Decision-Making Theory
This research aims to develop a rational theory of dynamic decision-making under uncertainty, providing a solid foundation for enhancing decision-making processes in both human and technological agents. The results to date have demonstrated significant effectiveness across a wide range of fields, including medical diagnostics, manufacturing process control, motion control in complex robotic systems, economic decision-making, e-democracy, transportation, and more.
Our research focuses on advancing decision-making (DM) for agents—whether human, devices, or a combination of both. These agents interact with, or sometimes simply observe, their environment and make decisions to achieve their goals. Unlike decisions made by large language models, which only replicate patterns from past data without true reasoning, our approach to rational decision-making is a thoughtful process that integrates prior knowledge, individual goals, and the optimization of outcomes based on specific decision-making objectives and context.
Our results are built around three key components:
Axiomatic prescriptive decision-making theory
This theory models the agent's environment and decision goals through probabilities, extending existing theories based on the optimization of expected utility [1].
Automatic mapping of decision goals
We offer robust and well-grounded methods for translating available informal or incomplete knowledge and decision goals into probabilities, while accounting for the limited resources of real agents, such as expertise, time for deliberation, data availability, computing power, and energy requirements [2].
Efficient Knowledge Transfer
Our research introduces a universal correspondence function that identifies and learns similarities between two related decision-making tasks, enabling efficient knowledge transfer. The effectiveness of this transfer has been demonstrated in a video game environment [3].
Related publications:
- KÁRNÝ, Miroslav. Prescriptive Inductive Operations on Probabilities Serving to Decision-Making Agents. IEEE Transactions on Systems Man Cybernetics-Systems, 2022, 52(4):2110-2120.
- KÁRNÝ, Miroslav, GUY, Tatiana Valentine, Preference Elicitation within Framework of Fully Probabilistic Design of Decision Strategies, IFAC-Papers on Line: Proceedings of the 13th IFAC Workshop on Adaptive and Learning Control Systems 2019, 52(29):239-244.
- RUMAN, Marko; GUY, Tatiana Valentine. Knowledge Transfer in Deep Reinforcement Learning via an RL-Specific GAN-Based Correspondence Function, IEEE Access, 2024, 12.
Contact person