Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

CIG
2005
IEEE

favoriteEmaildiscussreport

120views Applied Computing» more CIG 2005»

Adapting Reinforcement Learning for Computer Games: Using Group Utility Functions

13 years 10 months ago

Adapting Reinforcement Learning for Computer Games: Using Group Utility Functions

Download cswww.essex.ac.uk

AbstractGroup utility functions are an extension of the common team utility function for providing multiple agents with a common reinforcement learning signal for learning cooperative behaviour. In this paper we describe what group utility functions are and suggest using them to provide non-player computer game character behaviours. As yet, reinforcement learning techniques have very rarely been used for computer game character speciﬁcation. Here we show the results of using a group utility function to learn an equilibrium between two computer game characters and compare this against the performance of the two agents learning independently. We also explain how group utility functions could be applied to learn equilibria between groups of agents. We highlight some implementation issues arising from using a commercial computer game engine for multi-agent reinforcement learning experiments.

Jay Bradley, Gillian Hayes

Real-time Traffic

CIG 2005 | Group Utility Functions | Reinforcement Learning | Utility Functions |

claim paper

Related Content

» Automatic computer game balancing a reinforcement learning approach

» Utile Distinctions for Relational Reinforcement Learning

» Learning to play Tetris applying reinforcement learning methods

» Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning

» Reinforcement learning for games failures and successes

» Combining ModelBased MetaReasoning and Reinforcement Learning for Adapting GamePlaying Age...

» Asymmetric Multiagent Reinforcement Learning

» Coordination in utility managed multiagent groups

» Feature Construction for Reinforcement Learning in Hearts

Post Info
More Details (n/a)

Added	24 Jun 2010
Updated	24 Jun 2010
Type	Conference
Year	2005
Where	CIG
Authors	Jay Bradley, Gillian Hayes

Comments (0)