Tomasz Tajmajer

Papers

Total Citations

H-Index

About

Tomasz Tajmajer is a researcher whose work sits at the intersection of artificial intelligence and multi-objective decision-making, with a particular focus on reinforcement learning. His primary research area centers on extending Deep Q-Networks (DQNs)—traditionally designed for single-objective problems—to complex environments where agents must balance competing goals. Tajmajer’s major contributions include the development of two innovative frameworks: the "Modular Multi-Objective Deep Reinforcement Learning with Decision Values" (2018, 38 citations) and the "Multi-Objective Deep Q-Learning with Subsumption Architecture" (2017, 7 citations). These works address a critical gap in AI, enabling agents to learn from high-level visual perception while pursuing multiple, often conflicting objectives—a challenge common in robotics, games, and autonomous systems. By introducing modular architectures and decision-value mechanisms, Tajmajer has provided practical solutions for training agents that can prioritize and adapt in dynamic environments. His research is particularly notable for its potential to advance real-world applications, from robotic navigation to game AI, where single-objective approaches fall short. With a growing citation impact, Tajmajer is establishing himself as a key contributor to the evolution of multi-objective reinforcement learning.