Sabiia Seb
PortuguêsEspañolEnglish
Embrapa
        Busca avançada

Botão Atualizar


Botão Atualizar

Ordenar por: RelevânciaAutorTítuloAnoImprime registros no formato resumido
Registros recuperados: 22
Primeira ... 12 ... Última
Imagem não selecionada

Imprime registro no formato completo
Abstraction for Genetics-Based Reinforcement Learning InTech
Will Browne; Dan Scott; Charalambos Ioannides.
Abstraction may appear a trivial task for humans and the positive results from this work intuitive, but abstraction has not been routinely used in genetics-based reinforcement learning. One reason is that the time each iteration requires is an important consideration and abstraction increases the time for each iteration. Typically XCS takes 20 minutes to play 1000 games (and remains constant), mXCS with abstraction takes 20 minutes for 100 games (although this can vary greatly depending on the choice of parameters) and the Q-Learning algorithm ranges from 5 minutes for 1000 games initially to 90 minutes for 1000 games after 100,000 games training. However, given a fixed amount of time to train all three algorithms mXCS with abstraction would perform the...
Tipo: 10 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/abstraction_for_genetics-based_reinforcement_learning
Imagem não selecionada

Imprime registro no formato completo
An Extension of Finite-state Markov Decision Process and an Application of Grammatical Inference InTech
Takeshi Shibata; Ryo Yoshinaka.
In this chapter, we presented two new notions. One is an extension of episodic finite-state MDPs from the point of view of grammatical formalism. We can extend well-known methods of reinforcement learning and apply them to this extension easily. The other is the probabilistic generalities of grammars and unifiability of them. This notion plays an important role to apply the recent results of grammatical inference area. The difficulty with
Tipo: 5 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/an_extension_of_finite-state_markov_decision_process_and_an_application_of_grammatical_inference
Imagem não selecionada

Imprime registro no formato completo
Application on Reinforcement Learning for Diagnosis Based on Medical Image InTech
Stelmo Magalhaes Barros Netto; Vanessa Rodrigues Coelho Leite; Aristofanes Correa Silva; Anselmo Cardoso de Paiva; Areolino de Almeida Neto.
This work presents an overview of current work applying reinforcement learning in medical image applications, presenting a detailed illustration of a particular use for lung nodules classification. The addressed application of reinforcement learning to solve the problem of lung nodules classification used the 3D geometric nodules characteristics to guide the classification. Even though the results are preliminary we may see that the obtained results are very encouraging, demonstrating that the reinforcement learning classifier using characteristics of the nodules’ geometry can effectively classify benign from malignant lung nodules based on CT images. On the other side, we may observe that this is a machine learning that is not commonly applied to medical...
Tipo: 20 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/application_on_reinforcement_learning_for_diagnosis_based_on_medical_image
Imagem não selecionada

Imprime registro no formato completo
Decentralized Reinforcement Learning for the Online Optimization of Distributed Systems InTech
Jim Dowling; Seif Haridi.
This research was supported by a Marie Curie Intra-European Fellowship within the 6th European Community Framework Programme. The authors would like to thank Jan Sacha for an implementation of CRL in Java on which the experiments in this paper are based.
Tipo: 8 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/decentralized_reinforcement_learning_for_the_online_optimization_of_distributed_systems
Imagem não selecionada

Imprime registro no formato completo
Dynamics of the Bush-Mosteller Learning Algorithm in 2x2 Games InTech
Luis R. Izquierdo; Segismundo S. Izquierdo.
This chapter has characterised the behaviour of the Bush-Mosteller (Bush & Mosteller, 1955) aspiration-based reinforcement learning model in 2x2 games. The dynamics of this process depend mainly on three features: The speed of learning. The existence of self-reinforcing equilibria (SREs). SREs are states which are particularly relevant for the ultralong-run or asymptotic behaviour of the process. The existence of self-correcting equilibria (SCEs). SCEs are states which are particularly relevant for the transient behaviour of the process with low learning rates. With high learning rates, the model approaches its asymptotic behaviour fairly quickly. If there are SREs, such asymptotic dynamics are concentrated on the SREs of the system. With low learning...
Tipo: 11 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/dynamics_of_the_bush-mosteller_learning_algorithm_in_2x2_games
Imagem não selecionada

Imprime registro no formato completo
Inductive Approaches Based on Trial/Error Paradigm for Communications Network InTech
Abdelhamid Mellouk.
Due to the growing needs in telecommunications (VoD, Video-Conference, VoIP, etc.) and the diversity of transported flows, communication networks does not meet the requirements of the future integrated-service networks that carry multimedia data traffic with a high QoS. The main drivers of this evolution are the continuous growth of the bandwidth requests, the promise of cost improvements and finally the possibility of increasing profits by offering new services. First, it does not support resource reservation which is primordial to guarantee an end-to-end Qos (bounded delay, bounded delay jitter, and/or bounded loss ratio). Second, data packets may be subjected to unpredictable delays and thus may arrive at their destination after the expiration time,...
Tipo: 18 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/inductive_approaches_based_on_trial_error_paradigm_for_communications_network
Imagem não selecionada

Imprime registro no formato completo
Interaction Between the Spatio-Temporal Learning Rule (Non Hebbian) and Hebbian in Single Cells: A Cellular Mechanism of Reinforcement Learning InTech
Minoru Tsukada.
1
Tipo: 6 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/interaction_between_the_spatio-temporal_learning_rule__non_hebbian__and_hebbian_in_single_cells__a_c
Imagem não selecionada

Imprime registro no formato completo
Model-Free Learning Control of Chemical Processes InTech
S. Syafiie; F. Tadeo; E. Martinez.
Tipo: 16 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/model-free_learning_control_of_chemical_processes
Imagem não selecionada

Imprime registro no formato completo
Modular Learning Systems for Behavior Acquisition in Multi-Agent Environment InTech
Yasutake Takahashi; Minoru Asada.
In this chapter, we have showed a method by which multiple modules are assigned to different situations caused by the alternation of the other agent's policy so that an agent may learn purposive behaviors for the specified situations as consequences of the other agent's behaviors. Macro actions are introduced to realize simultaneous learning of competitive behaviors in a multi-agent system. Results of a soccer situation and the importance of the learning scheduling in case of none-simultaneous learning without macro actions, as well as the validity of the macro actions in case of simultaneous learning in the multi-agent system, were shown. We have also showed another learning system using the state values instead of the physical sensor values and macro...
Tipo: 12 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/modular_learning_systems_for_behavior_acquisition_in_multi-agent_environment
Imagem não selecionada

Imprime registro no formato completo
Multi-Automata Learning InTech
Verbeeck Katja; Nowe Ann; Vrancx Peter; Peeters Maarten.
In this chapter we have demonstrated that Learning Automata are interesting building blocks for multi-agent Reinforcement learning algorithms. LA can be viewed as policy iterators, that update their action probabilities based on private information only. Even in multi-automaton settings, each LA is updated using only the environment response, and not on the basis of any knowledge regarding the other automata, i.e. nor their strategies, nor their feedback. As such LA based agent algorithms are relatively simple and the resulting multi-automaton systems can still be treated analytically. Convergence proofs already exist for a variety of settings ranging from a single automaton model acting in a simple stationary random environment to a distributed automata...
Tipo: 9 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/multi-automata_learning
Imagem não selecionada

Imprime registro no formato completo
Neural Forecasting Systems InTech
Takashi Kuremoto; Masanao Obayashi; Kunikazu Kobayashi.
Though RL has been developed as one of the most important methods of machine learning, it is still seldom adopted in forecasting theory and prediction systems. Two kinds of neural forecasting systems using SGA learning were described in this chapter, and the experiments of training and short-term forecasting showed their successful performances comparing with the conventional NN prediction method. Though the iterations of MLP with SGA and SOFNN with SGA in training experiments took more than that of MLP with BP, both of their computation time were not more than a few minutes by a computer with 3.0GHz CPU. A problem of these RL forecasting systems is that the value of reward in SGA algorithm influences learning convergence seriously, the optimum reward...
Tipo: 1 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/neural_forecasting_systems
Imagem não selecionada

Imprime registro no formato completo
Optimising Spoken Dialogue Strategies within the Reinforcement Learning Paradigm InTech
Olivier Pietquin.
This chapter described a formal description of a man-machine spoken dialogue suitable to introduce a mapping between man-machine dialogues and (partially observable) Markov decision processes. This allows data-driven optimization of a dialogue manager's interaction strategy using the reinforcement learning paradigm. Yet, such an optimization process often requires tenths of thousands of dialogues which are not accessible through real interactions with human users because of time and economical constraints. Expanding existing databases by means of dialogue simulation is a solution to this problem and several approaches can be envisioned as discussed in section 0. In this context, we described the particular task of speech-based database querying and its...
Tipo: 13 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/optimising_spoken_dialogue_strategies_within_the_reinforcement_learning_paradigm
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Evolutionary Learning for Neuro-Fuzzy Controller Design InTech
Cheng-Jian Lin.
A novel reinforcement sequential-search-based genetic algorithm (R-SSGA) is proposed. The better chromosomes will be initially generated while the better mutation points will be determined for performing efficient mutation. We formulate a number of time steps before failure occurs as the fitness function. The proposed R-SSGA method makes the design of TSK-Type fuzzy controllers more practical for real-world applications, since it greatly lessens the quality and quantity requirements of the teaching signals. Two typical examples were presented to show the fundamental applications of the proposed R-SSGA method. Simulation results have shown that 1) the R-SSGA method converges quickly; 2) the R-SSGA method requires a small number of population sizes (only 4);...
Tipo: 3 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_evolutionary_learning_for_neuro-fuzzy_controller_design
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Learning Embedded in Brains and Robots InTech
Cornelius Weber; Mark Elshaw; Stefan Wermter; Jochen Triesch; Christopher Willmot.
This work has been funded partially by the EU project MirrorBot, grant IST-2001-35282, and NEST-043374 coordinated by SW. CW, JT and AF are supported by the Hertie Foundation, and the EU projects PLICON, grant MEXT-CT-2006-042484, and Daisy, grant FP6-2005015803. Urs Bergmann provided feedback on the manuscript.
Tipo: 7 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_learning_embedded_in_brains_and_robots
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Learning for Building Environmental Control InTech
Konstantinos Dalamagkidis; Dionysia Kolokotsa.
1
Tipo: 15 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_learning_for_building_environmental_control
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Learning in System Identification InTech
Mariela Cerrada; Jose Aguilar.
This work has been partially presented in the International Symposium on Neural Networks ISNN 2006.
Tipo: 2 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_learning_in_system_identification
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Learning to Support Meta-Level Control in Air Traffic Management InTech
Daniela P. Alves; Li Weigang; Bueno B. Souza.
This research presented a solution for Meta-Level Control application and reinforcement learning in the decision process to improve the efficiency for the exchange of messages within a distributed system in ATFM. As a part of the research of the Evaluation and Decision Support Module (MAAD), the reinforcement learning approach was applied and developed as a sub-module (MRL) with adaptation of two algorithms: Q-learning and SARSA. The Meta-Level Control was developed as another sub-module (MDC) for making decision regarding information process. One of the advantages of the use of reinforcement learning is that the agents acquire experience during the iteration process with the environment. As a similar form of learning, it utilizes system performance as...
Tipo: 22 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_learning_to_support_meta-level_control_in_air_traffic_management
Imagem não selecionada

Imprime registro no formato completo
Reinforcement Learning-Based Supervisory Control Strategy for a Rotary Kiln Process InTech
Xiaojie Zhou; Heng Yue; Tianyou Chai.
In this chapter, we focus on the discussion about an implementation strategy of how to employ reinforcement learning in control of a typical complex industrial process to enhance control performance and adaptability for the variations of operating conditions of the automatic control system. Operation of large rotary kilns is difficult and relies on experienced human operators observing the burning status, because of their inherent complexities. Thus the problem of human-machine coordination is addressed when we design the rotary kiln control system, and the human intervention and adjustment can be introduced. Except for emergent operation conditions that need urgent human operation for system safety, the fact is observed that human interventions to the...
Tipo: 17 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/reinforcement_learning-based_supervisory_control_strategy_for_a_rotary_kiln_process
Imagem não selecionada

Imprime registro no formato completo
RL Based Decision Support System for u-Healthcare Environment InTech
Devinder Thapa; In-Sung Jung; Gi-Nam Wang.
This paper presents and describes a Reinforcement Learning agent based model used for information acquiring and real time decision support system at emergency circumstances. The well known reinforcement learning is utilized for modeling emergency u-Healthcare system. Markov decision process is also employed to provide clear mathematical formulation in order to connect reinforcement learning as well as to express integrated agent system. This method will be highly effective for the real time diagnosis and treatment of high risk patient during the emergency circumstances, when they are away from the hospital premises. Looking at the growing increase in the research area of ubiquitous devices this approach seems to be very beneficial and life saving for the...
Tipo: 21 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/rl_based_decision_support_system_for_u-healthcare_environment
Imagem não selecionada

Imprime registro no formato completo
Superposition-Inspired Reinforcement Learning and Quantum Reinforcement Learning InTech
Chun-Lin Chen; Dao-Yi Dong.
According to the existing problems in RL area, such as low learning speed and tradeoff between exploration and exploitation, SIRL and QRL methods are introduced based on the theory of RL and quantum computation in this chapter, which follows the developing roadmap from the superposition-inspired methods to the RL methods in quantum systems. Just as simulated annealing algorithm comes from mimicking the physical annealing process, quantum characteristics also broaden our mind and provide alternative approaches to novel RL methods. In this chapter, SIRL method emphasizes the exploration policy and uses a probabilistic action selection method that is inspired by the state superposition principle and collapse postulate. The experiments, which include a puzzle...
Tipo: 4 Palavras-chave: Reinforcement Learning.
Ano: 2008 URL: http://www.intechopen.com/articles/show/title/superposition-inspired_reinforcement_learning_and_quantum_reinforcement_learning
Registros recuperados: 22
Primeira ... 12 ... Última
 

Empresa Brasileira de Pesquisa Agropecuária - Embrapa
Todos os direitos reservados, conforme Lei n° 9.610
Política de Privacidade
Área restrita

Embrapa
Parque Estação Biológica - PqEB s/n°
Brasília, DF - Brasil - CEP 70770-901
Fone: (61) 3448-4433 - Fax: (61) 3448-4890 / 3448-4891 SAC: https://www.embrapa.br/fale-conosco

Valid HTML 4.01 Transitional