• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.388-394
• /
• 2001

Reinforcement learning is a kind of unsupervised learning methods that an agent control rules from experiences acquired by interactions with environment. The eligibility is used to resolve the credit-assignment problem which is one of important problems in reinforcement learning, Conventional eligibilities such as the accumulating eligibility and the replacing eligibility are ineffective in use of rewards acquired in learning process, since on1y one executed action for a visited state is learned. In this paper, we propose a new eligibility, called the distributed eligibility, with which not only an executed action but also neighboring actions in a visited state are to be learned. The fuzzy Q-learning algorithm using the proposed eligibility is applied to a cart-pole balancing problem, which shows the superiority of the proposed method to conventional methods in terms of learning speed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.9
• /
• pp.2027-2034
• /
• 1997

Frame relay is a fast packet switching technology that performs relaying and multiplexing frames with variable lengths over a wide area link at the T1 or E1 speed, by elminating error and flow control in the network. In frame relay networks, congestion control is typically performed through the rate enforcement with a discard eligibility (DE) bit, and the explicit negative feedback meachanisms using explicit congetion notification bits. In this paper, we consider the congestiong control scheme using the rate enforcement mechanism with DE bit for frame relay network. Assuming that each frame with exponentially distributed length arrives according to the Poission fashion, we can treat the frame relay switch as an M/M/1/K priority queueing system with pushout basis. We analyze and present the blocking probabilities and waiting time distributions of frames.