• Journal of the Korean Mathematical Society
• /
• v.56 no.1
• /
• pp.53-65
• /
• 2019

Recently, Chung and Lee [2] introduced the notion of topological stability for a finitely generated group action, and proved a group action version of the Walters's stability theorem. In this paper, we introduce the concepts of continuous shadowing and continuous inverse shadowing of a finitely generated group action on a compact metric space X with respect to various classes of admissible pseudo orbits and study the relationships between topological stability and continuous shadowing and continuous inverse shadowing property of group actions. Moreover, we introduce the notion of structural stability for a finitely generated group action, and we prove that an expansive action on a compact manifold is structurally stable if and only if it is continuous inverse shadowing.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.4
• /
• pp.270-275
• /
• 2016

We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

• Journal of the Chungcheong Mathematical Society
• /
• v.32 no.4
• /
• pp.509-524
• /
• 2019

Let Act(G, X) be the set of all continuous actions of a finitely generated group G on a compact metric space X. In this paper, we study the concepts of topologically stable points and continuous shadowable points of a group action T ∈ Act(G, X). We show that if T is expansive then the set of continuous shadowable points is contained in the set of topologically stable points.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.471-476
• /
• 2016

In this paper, recognition system for continuous human action is explained by using motion history image and histogram of oriented gradient with spotter model based on depth information, and the spotter model which performs action spotting is proposed to improve recognition performance in the recognition system. The steps of this system are composed of pre-processing, human action and spotter modeling and continuous human action recognition. In pre-processing process, Depth-MHI-HOG is used to extract space-time template-based features after image segmentation, and human action and spotter modeling generates sequence by using the extracted feature. Human action models which are appropriate for each of defined action and a proposed spotter model are created by using these generated sequences and the hidden markov model. Continuous human action recognition performs action spotting to segment meaningful action and meaningless action by the spotter model in continuous action sequence, and continuously recognizes human action comparing probability values of model for meaningful action sequence. Experimental results demonstrate that the proposed model efficiently improves recognition performance in continuous action recognition system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• Journal of the Korean Mathematical Society
• /
• v.32 no.3
• /
• pp.573-582
• /
• 1995

J.Milnor[Mi2] has introduced the notion of directional entropy in his study of Cellular Automata. Cellular Automaton map can be considered as a continuous map from a space $K^Z^n$ to itself which commute with the translation of the lattice $Z^n$. Since the space $K^Z^n$ is compact, map S is uniformly continuous. Hence S is a block map(a finite code)[He]. (S is said to have a finite memory.) In the case of n = 1, we have a shift map, T on $K^Z$, and a block map S and they together generate a $Z^2$ action.

• Korean Journal of Mathematics
• /
• v.5 no.2
• /
• pp.169-176
• /
• 1997

The purpose of this note is to compare two known results related to the lifting problem of an action of a topological group G on a G-space X to a coverring space of X.

• Korean Institute of Interior Design Journal
• /
• v.23 no.5
• /
• pp.76-85
• /
• 2014

When conscious and unconscious exploring information of space-visitors which is contained in the information acquired in the process of seeing any space is analyzed, it can be found what those visitors pick up as factors in the space for its selection as visual information in order to put it into action. This study, with the object of the space reproduced in three dimensions from the cafe which was visited for conversation, has analyzed the process of acquiring space-information by sex to find out the features of scanning path, findings of which are the followings. First, the rate of scanning type of males was "Combination (50.5%)- Circulation (31.0%) and that of females "Horizontal (32.5%) - Combination (32.1%)", which shows that there was a big difference by sex in the scanning path which took place in the process of observing any space. Second, when the features of continuous observation frequency by sex is looked into, the trends of increased "horizontal" scanning and decreased "Combination" scanning of both showed the same as the frequency of continuous observations increased, while in case of "Circulation" scanning, that of females was found to decrease but that of males showed the aspect of confusion. Third, the 'Combination' scanning of males was found strong at the short observation time with three times of continuous observation frequency defined as "Attention Concentration" while the distinct feature was seen that the scanning type was dispersed to "combination-circulation" as the frequency of continuous observation increased. Females start the information acquirement with "combination-circulation" but in the process of visual appreciation they showed a strong "Horizontal" These scanning features can be defined as those by sex for acquiring space information and therefore are very significant because they are fundamental studies which will enable any customized space-design by sex.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.587-592
• /
• 2003

Many real world control problems have continuous states and actions. When the state space is continuous, the reinforcement learning problems involve very large state space and suffer from memory and time for learning all individual state-action values. These problems need function approximators that reason action about new state from previously experienced states. We introduce Fuzzy Q-Map that is a function approximators for 1 - step Q-learning and is based on fuzzy clustering. Fuzzy Q-Map groups similar states and chooses an action and refers Q value according to membership degree. The centroid and Q value of winner cluster is updated using membership degree and TD(Temporal Difference) error. We applied Fuzzy Q-Map to the mountain car problem and acquired accelerated learning speed.

• Journal of KIISE:Software and Applications
• /
• v.30 no.11
• /
• pp.1054-1061
• /
• 2003

Q-Learning, a representative algorithm of reinforcement learning, experiences repeatedly until estimation values about all state-action pairs of state space converge and achieve optimal policies. When the state space is high dimensional or continuous, complex reinforcement learning tasks involve very large state space and suffer from storing all individual state values in a single table. We introduce Q-Map that is new function approximation method to get classified policies. As an agent learns on-line, Q-Map groups states of similar situations and adapts to new experiences repeatedly. State-action pairs necessary for fine control are treated in the form of rule. As a result of experiment in maze environment and mountain car problem, we can achieve classified knowledge and extract easily rules from Q-Map