Sciweavers

458 search results - page 31 / 92
» Q-Decomposition for Reinforcement Learning Agents
Sort
View
ROBOCUP
2005
Springer
134views Robotics» more  ROBOCUP 2005»
14 years 1 months ago
Simultaneous Learning to Acquire Competitive Behaviors in Multi-agent System Based on Modular Learning System
The existing reinforcement learning approaches have been suffering from the policy alternation of others in multiagent dynamic environments. A typical example is a case of RoboCup...
Yasutake Takahashi, Kazuhiro Edazawa, Kentarou Nom...
CIG
2005
IEEE
14 years 1 months ago
Adapting Reinforcement Learning for Computer Games: Using Group Utility Functions
AbstractGroup utility functions are an extension of the common team utility function for providing multiple agents with a common reinforcement learning signal for learning cooperat...
Jay Bradley, Gillian Hayes
ATAL
2008
Springer
13 years 9 months ago
Graph Laplacian based transfer learning in reinforcement learning
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
Yi-Ting Tsao, Ke-Ting Xiao, Von-Wun Soo
AAAI
2006
13 years 9 months ago
Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance
As robots become a mass consumer product, they will need to learn new skills by interacting with typical human users. Past approaches have adapted reinforcement learning (RL) to a...
Andrea Lockerd Thomaz, Cynthia Breazeal
AAAI
1996
13 years 9 months ago
Evolution-Based Discovery of Hierarchical Behaviors
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
Justinian P. Rosca, Dana H. Ballard