Modeling of autonomous problem solving process by dynamic construction of task models in multiple tasks environment

Authors:
Yu Ohigashi;Takashi Omori
Affiliations:
Graduate School of Information Science, Hokkaido University, Kita, Kita, Sapporo, Hokkaido, Japan;Tamagawa University Research Institute, Tamagawa University, Machida, Tokyo, Japan
Venue:
Neural Networks - 2006 Special issue: Neurobiology of decision making
Year:
2006

Citing 8
Cited 0

Integrated architecture for learning, planning, and reacting based on approximating dynamic programming

Proceedings of the seventh international conference (1990) on Machine learning
Clustering learning tasks and the selective cross-task transfer of knowledge

Learning to learn
Multiple paired forward and inverse models for motor control

Neural Networks - Special issue on neural control and robotics: biology and technology
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Multiple model-based reinforcement learning

Neural Computation
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
Acquisition of learning processing in a navigation task using a functional parts combination model

Systems and Computers in Japan
Acceleration of game learning with prediction-based reinforcement learning: toward the emergence of planning behavior

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional reinforcement learning (RL) supposes a complex but single task to be solved. When a RL agent faces a task similar to a learned one, the agent must relearn the task from the beginning because it doesn't reuse the past learned results. This is the problem of quick action learning, which is the foundation of decision making in the real world. In this paper, we suppose agents that can solve a set of tasks similar to each other in a multiple tasks environment, where we encounter various problems one after another, and propose a technique of action learning that can quickly solve similar tasks by reusing previously learned knowledge. In our method, a model-based RL uses a task model constructed by combining primitive local predictors for predicting task and environmental dynamics. To evaluate the proposed method, we performed a computer simulation using a simple ping-pong game with variations.