Bálint Takács

Learn More
In this paper ε-MDP-models are introduced and convergence theorems are proven using the generalized MDP framework of Szepesvári and Littman. Using this model family, we show that Q-learning is capable of finding near-optimal policies in varying environments. The potential of this new family of MDP models is illustrated via a reinforcement learning algorithm(More)
We show that explicit MPC solutions admit a closed-form solution which does not require the storage of critical regions. Therefore significant amount of memory can be saved. In fact, not even the construction of such regions is required. Instead, all possible optimal active sets are first extensively enumerated. Then, for each optimal, only the analytical(More)
We propose a novel method for multi-robot plan adaptation which can be used for adapting existing spatial plans of robotic teams to new environments or imitating collaborative spatial teamwork of robots in novel situations. The algorithm selects correspondences between previous and current spatial features by the application of pairwise constraints, and(More)
We examine the application of spectral clustering for breaking up the behavior of a multi-agent system in space and time into smaller, independent elements. We propose clustering observations of individual entities in order to identify significant changes in the parameter space (like spatial position) and detect temporal alterations of behavior within the(More)
We examine the application of spectral clustering for breaking up the behavior of a multi-agent system in space and time into smaller, independent elements. We cluster observations of individual entities in order to identify significant changes in the parameter space (like spatial position)and detect temporal alterations of behavior within the same(More)
We present a prototype of a recently proposed two stage model of the entorhinal-hippocampal loop. Our aim is to form a general computational model of the sensory neocortex. The model--grounded on pure information theoretic principles--accounts for the most characteristic features of long-term memory (LTM), performs bottom-up novelty detection, and supports(More)
Explicit Model Predictive Control (MPC) is an attractive control strategy, especially when one aims at a fast, computationally less demanding implementation of MPC. Although leading to a fast implementation of optimization based control, the main downside of explicit MPC is its high complexity in terms of memory occupancy, which often limits practical(More)