Warsaw, Mazowieckie, Poland
I'm a machine learning researcher with a strong mathematical background. I finished a Master's degree in machine learning and a Master's degree in mathematics. I graduated from a class for exceptionally gifted students in XIV LO im. Stanisława Staszica and successfully competed in the Polish Mathematical Olympiad and the International Mathematics Competition. I conducted research on commutative algebra and algebraic geometry with Dr. Hab. Joachim Jelisiejew, which resulted in the publication "Irreversibility of structure tensors of modules" (https://doi.org/10.1007/s13348-022-00361-w) and the paper "Iarrobino's decomposition for self-dual modules", available on ArXiv (https://arxiv.org/abs/2405.13829). Now I'm conducting research in machine learning. My specialty field is reinforcement learning. With a group from the Polish Academy of Sciences I co-created the Latent Subgoal Search algorithm (which is yet to be extended). I worked on a proactive cloud solver based on RL for 7bulls.com and developed RL methods for investing in currency pairs for AI Investments. Currently I'm pursuing a PhD at the University of Warsaw in the topic of reinforcement learning. I'm also employed at the IDEAS Research Institute. We conduct research on the topic of communication for multi-agent reinforcement learning. I'm also working on the application of reinforcement learning for the tension regulation in hanger rods with a group from the Polish Academy of Sciences under an NCBR grant. For references one can email [email protected].
Research on the topics from reinforcement learning, focusing on multi-agent reinforcement learning, including such topics like: communication between agents, exploration technoques, value decompositiom methods, algorithms for continuous action space
Dissertation topic: “Algorithms for multi-agent reinforcement learning: a game theory based approach", research on the aspects of multi-agent reinforcement learning, like credit assignment and action-value function decomposition, communication between the agents, transfer of known algorithms to the continuous action domain. In cooperation with the team from IDEAS NCBR
Application of reinforcement learning to hanger rod tension adjustment based on the PPO algorithm and the customized environment
Analysis of reinforcement learning methods for currency pairs based on the PPO and Asynchronous PPO algorithms, Random Destillation Networks and the customized environment. References: [email protected]
Inventing and implementing the Latent Subgoal Search algorithm, a modification of the Subgoal Search algorithm - an algorithm connecting planning and hierarchical reinforcement learning. Our method added the latent representations to the model, as a neural network the Transformer architecture was utilized. Work done as the Master's thesis in machine learning.