4 papers
Decentralized MCTS via Learned Teammate Models
Aleksander Czechowski, Frans A. Oliehoek
Decentralized online planning can be an attractive paradigm for cooperative multi-agent systems, due to improved scalability and robustness. A key difficulty of such approach lies…
Influence-aware Memory Architectures for Deep Reinforcement Learning
Miguel Suau, Jinke He, Elena Congeduti +3
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the…
Rigorous numerics for a singular perturbation problem
Aleksander Czechowski
Fast-slow systems are notoriously difficult to analyze with rigorous numerics, since the qualitative properties of the solution space change fundamentally when the so-called small…
ICA based on Split Generalized Gaussian
P. Spurek, P. Rola, J. Tabor +1
Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent. Most popular…