Training and delayed reinforcements in Q-learning agents

Caironi, P.; Dorigo, Marco

doi:10.1002/(sici)1098-111x(199710)12:10<695::aid-int1>3.0.co;2-t

Cited by 20 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The actor-critic algorithm is much simpler than Q-learning in the computation, 19 can determine the optimal policy, and effectively applied to control the tasks. 20,21 Markov chain model for investment…”

Section: Reinforcement Learningmentioning

confidence: 99%

An actor-critic-based portfolio investment method inspired by benefit-risk optimization

Tang

2018

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

How to get maximal benefit within a range of risk in securities market is a very interesting and widely concerned issue. Meanwhile, as there are many complex factors that affect securities' activity, such as the risk and uncertainty of the benefit, it is very difficult to establish an appropriate model for investment. Aiming at solving the curse of dimension and model disaster caused by the problem, we use the approximate dynamic programming to set up a Markov decision model for the multi-time segment portfolio with transaction cost. A model-based actor-critic algorithm under uncertain environment is proposed, where the optimal value function is obtained by iteration on the basis of the constrained risk range and a limited number of funds, and the optimal investment of each period is solved by using the dynamic planning of limited number of fund ratio. The experiment indicated that the algorithm could get a stable investment, and the income could grow steadily.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

An actor-critic-based portfolio investment method inspired by benefit-risk optimization

Tang

2018

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

show abstract

“…A good solution to this problem might be to exploit both mechanisms, in order to get the best out of each. Even if a few steps in this direction have already been made ( [5,26]), no final solution has been proposed yet.…”

Section: About Learning and Trainingmentioning

confidence: 99%

“…A second example of the application of the BAT methodology is HAMSTER, a mobile robot based on a commercial platform, whose task is to bring "food" to its "nest." 5 We shall not describe all steps in the development of this robot, but confine ourselves to the description of the main differences with respect to AM.…”

Section: Case 2: Hamstermentioning

confidence: 99%

Behavior analysis and training-a methodology for behavior engineering

Colombetti

Dorigo²,

Borghi³

1996

IEEE Trans. Syst., Man, Cybern. B

View full text Add to dashboard Cite

We propose Behavior Engineering as a new technological area whose aim is to provide methodologies and tools for developing autonomous robots. Building robots is a very complex engineering enterprise that requires the exact definition and scheduling of the activities which a designer, or a team of designers, should follow. Behavior Engineering is, within the autonomous robotics realm, the equivalent of more established disciplines like Software Engineering and Knowledge Engineering. In this article we first give a detailed presentation of a Behavior Engineering methodology, which we call Behavior Analysis and Training (BAT), where we stress the role of learning and training. Then we illustrate the application of the BAT methodology to three cases involving different robots: two mobile robots and a manipulator. Results show the feasibility of the proposed approach.

show abstract

“…We try to improve ACS technique by adding Q learning [9] concept. This Ant-Q method can solve SMP problem for various requirements.…”

Section: Introductionmentioning

confidence: 99%

“…(1,10), (2,8), (3,5), (4,2),(5,9),(6,7), (7,1), (8,4), (9,6), (10,3)   (1,6), (2,5), ((3,3), (4,10), (5,9), (6,4), (7,1),(8,7), (9,8), (10,2) (그림 2) 안정된 매칭의 결과들  는 수식(6)(7)과는 조금 다르다. …”

unclassified

Solving the Gale-Shapley Problem by Ant-Q learning

Kim¹,

Chung²

2011

The KIPS Transactions:PartB

View full text Add to dashboard Cite

In this paper, we propose Ant-Q learning Algorithm [1], which uses the habits of biological ants, to find a new way to solve Stable Marriage Problem(SMP) [3] presented by Gale-Shapley [2]. The issue of SMP is to find optimum matching for a stable marriage based on their preference lists (PL). The problem of Gale-Shapley algorithm is to get a stable matching for only male (or female). We propose other way to satisfy various requirements for SMP.ACS(Ant colony system) is an swarm intelligence method to find optimal solution by using phermone of ants. We try to improve ACS technique by adding Q learning [9] concept. This Ant-Q method can solve SMP problem for various requirements. The experiment results shows the proposed method is good for the problem.

show abstract

Training and delayed reinforcements in Q-learning agents

Cited by 20 publications

References 17 publications

An actor-critic-based portfolio investment method inspired by benefit-risk optimization

An actor-critic-based portfolio investment method inspired by benefit-risk optimization

Behavior analysis and training-a methodology for behavior engineering

Solving the Gale-Shapley Problem by Ant-Q learning

Contact Info

Product

Resources

About