R
Reinaldo A. C. Bianchi
Researcher at Centro Universitário da FEI
Publications - 102
Citations - 929
Reinaldo A. C. Bianchi is an academic researcher from Centro Universitário da FEI. The author has contributed to research in topics: Reinforcement learning & Robot. The author has an hindex of 14, co-authored 96 publications receiving 774 citations. Previous affiliations of Reinaldo A. C. Bianchi include University of São Paulo & Centra.
Papers
More filters
Journal ArticleDOI
Accelerating autonomous learning by using heuristic selection of actions
TL;DR: This paper investigates the use of heuristics for increasing the rate of convergence of RL algorithms and contributes with a new learning algorithm, Heuristically Accelerated Q-learning (HAQL), which incorporates heuristic for action selection to the Q-Learning algorithm.
Journal ArticleDOI
Heuristically-Accelerated Multiagent Reinforcement Learning
Reinaldo A. C. Bianchi,Murilo Fernandes Martins,Carlos H. C. Ribeiro,Anna Helena Reali Costa +3 more
TL;DR: The results show that even the most straightforward heuristics can produce virtually optimal action selection policies in much fewer episodes, significantly improving the performance of the HAMRL over vanilla RL algorithms.
Journal ArticleDOI
Transferring knowledge as heuristics in reinforcement learning
Reinaldo A. C. Bianchi,Luiz A. Celiberto,Paulo E. Santos,Jackson P. Matsuura,Ramon López de Mántaras +4 more
TL;DR: The goal of this paper is to propose and analyse a transfer learning meta-algorithm that allows the implementation of distinct methods using heuristics to accelerate a Reinforcement Learning procedure in one domain (the target) that are obtained from another domain ( the source domain).
Proceedings Article
Heuristic selection of actions in multiagent reinforcement learning
TL;DR: A set of empirical evaluations were conducted for the proposed algorithm in a simplified simulator for the robot soccer domain, and experimental results show that even very simple heuristics enhances significantly the performance of the multiagent reinforcement learning algorithm.
Book ChapterDOI
Heuristically Accelerated Q–Learning: A New Approach to Speed Up Reinforcement Learning
TL;DR: A new algorithm is presented that allows the use of heuristics to speed up the well-known Reinforcement Learning algorithm Q–learning, and an automatic method for the extraction of the heuristic function \(\mathcal{H}\) from the learning process is proposed, called Heuristic from Exploration.