49 citations · 127 across the 28 of their papers we have counts for
7 papers · 1 filter
Cognitive Deep Machine Can Train Itself
András Lőrincz, Máté Csákvári, Áron Fóthi +3
Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its ge…
Online variants of the cross-entropy method
Istvan Szita, Andras Lorincz
The cross-entropy method is a simple but efficient method for global optimization. In this paper we provide two online variants of the basic CEM, together with a proof of convergen…
Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs
Istvan Szita, Andras Lorincz
In this paper we propose a method that learns to play Pac-Man. We define a set of high-level observation and action modules. Actions are temporally extended, and multiple action mo…
Selection in Scale-Free Small World
Zs. Palotai, Cs. Farkas, A. Lorincz
In this paper we compare the performance characteristics of our selection based learning algorithm for Web crawlers with the characteristics of the reinforcement learning algorithm…
L1 regularization is better than L2 for learning and predicting chaotic systems
Z. Szabo, A. Lorincz
Emergent behaviors are in the focus of recent research interest. It is then of considerable importance to investigate what optimizations suit the learning and prediction of chaotic…
Reinforcement Learning with Linear Function Approximation and LQ control Converges
Istvan Szita, Andras Lorincz
Reinforcement learning is commonly used with function approximation. However, very few positive results are known about the convergence of function approximation based RL control a…
Kalman filter control in the reinforcement learning framework
Istvan Szita, Andras Lorincz
There is a growing interest in using Kalman-filter models in brain modelling. In turn, it is of considerable importance to make Kalman-filters amenable for reinforcement learning.…