This paper introduces a dynamic map for mobile robots that adapts continuously over time. It resolves the stabilityplasticity dilemma (the trade-off between adaptation to new patterns and preservation of old patterns) by representing the environment over multiple timescales simultaneously (5 in our experiments). A sample-based representation is proposed, where older memories fade at different r...

This paper addresses the problem of tracking multiple targets using a network of communicating robots and stationary sensors. We introduce a region-based approach which controls robot deployment at two levels. A coarse deployment controller distributes robots across regions using a topological map and density estimates, and a target-following controller attempts to maximize the number of tracke...

We demonstrate the possibility of optimal control of physical inventory systems in a nonstationary fitness terrain, based on the combined application of evolutionary search and adaptive critic terrain following. We show that adaptive critic based approximate dynamic programming techniques based on plant-controller Jacobeans can be used with systems characterized by discrete valued states and co...

Purpose Neural document clustering techniques, e.g., self-organising map (SOM) or growing neural gas (GNG), usually assume that textual information is stationary on the quantity. However, the quantity of text is ever-increasing. We propose a novel dynamic adaptive self-organising hybrid (DASH) model, which adapts to time-event news collections not only to the neural topological structure but al...

This paper provides a detailed comparative study concerning the performance of min-projection strategy (MPS) and model predictive control (MPC) systems to control the three-phase grid connected converters. To do so, first, the converter is modeled as a switched linear system. Then, the feasibility of the MPS technique is investigated and its stability criterion is derived as a lower limit on th...

Existing domain generalization aims to learn a generalizable model perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along indices. example, self-driving car with vision system drives from dawn dusk, sky darkening. Therefore, must be able adapt changes in ambient illuminations and continue drive safely road. In t...

Hierarchical Reinforcement Learning (HRL) provides an option to solve complex guidance and navigation problems with high-dimensional spaces, multiple objectives, a large number of states actions. The current HRL methods often use the same or similar reinforcement learning within one application so that objectives can be easily combined. Since there is not single method benefit all targets, hybr...

An exactly solvable model of a quantum spin interacting with a spin environment is considered. The interaction is chosen to be such that the state of the environment is conserved. The reduced density matrix of the spin is calculated for arbitrary coupling strength and arbitrary time. The stationary state of the spin is obtained explicitely in the t → ∞ limit. – 1 –