Real-time obstacle avoidance for manipulators and mobile robots
International Journal of Robotics Research
Advances in neural information processing systems 2
Technical Note: \cal Q-Learning
Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
DS-RT '04 Proceedings of the 8th IEEE International Symposium on Distributed Simulation and Real-Time Applications
Exploring the Spatial Density of Strategy Models in a Realistic Distributed Interactive Application
DS-RT '04 Proceedings of the 8th IEEE International Symposium on Distributed Simulation and Real-Time Applications
ACM Transactions on Modeling and Computer Simulation (TOMACS)
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part II
Hi-index | 0.00 |
Considering player entity's motion regularity into DR (Dead Reckoning) algorithm can improve its prediction accuracy in MMOG (Massively Multiplayer Online Games), a novel DR algorithm was proposed to solve this problem in this paper. First the artificial potential field model of player entities is created, and then the acceleration of player entities is weighted with the acceleration produced by the potential field force and the acceleration reckoned by the traditional DR algorithm. In order to calculate the weight, Q-Learning algorithm is used. The experiments show that the method can improve prediction accuracy and reduce the network traffic.