Published in 23rd International Symposium on Measurement and Control in Robotics (ISMCR), 2020
This paper investigates how to improve scene reconstruction in multi-agent Deep Reinforcement Learning
Recommended citation: M. Szemenyei and P. Reizinger. (2020). "Learning to Play Robot Soccer from Partial Observations" 23rd International Symposium on Measurement and Control in Robotics (ISMCR).
Published in 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
This paper introduces the attention mechanism in actor-critic architectures in the framework of curiosity-driven exploration.
Recommended citation: P. Reizinger and M. Szemenyei. (2020). "Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning" 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://arxiv.org/pdf/1910.10840.pdf
Published in International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO), 2019
This paper introduces a simulation suite for multi-agent Deep Reinforcement Learning (DynEnv) and applies attention-based techniques to utilize exploration.
Recommended citation: M. Szemenyei and P. Reizinger. (2019). "Attention-Based Curiosity in Multi-Agent Reinforcement Learning Environments" International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO).
Published in 5th International Conference on Learning, Optimization and Data Science, 2019
This paper introduces two widely-applicable regularization methods based on the direct modification of weight matrices.
Recommended citation: Reizinger P., Gyires-Tóth B. (2019) "Stochastic Weight Matrix-Based Regularization Methods for Deep Neural Networks.." Springer LNCS 1. 11943. https://arxiv.org/pdf/1909.11977