Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/78180
Title: IMPLANT: An integrated mdp and pomdp learning agent for adaptive games
Authors: Tan, C.T. 
Cheng, H.-L. 
Issue Date: 2009
Citation: Tan, C.T.,Cheng, H.-L. (2009). IMPLANT: An integrated mdp and pomdp learning agent for adaptive games. Proceedings of the 5th Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE 2009 : 94-99. ScholarBank@NUS Repository.
Abstract: This paper proposes an Integrated MDP and POMDP Learning AgeNT (IMPLANT) architecture for adaptation in modern games. The modern game world basically involves a human player acting in a virtual environment, which implies that the problem can be decomposed into two parts, namely a partially observable player model, and a completely observable game environment. With this concept, the IMPLANT architecture extracts both a POMDP and MDP abstract model from the underlying game world. The abstract action policies are then pre-computed from each model and merged into a single optimal policy. Coupled with a small amount of online learning, the architecture is able to adapt both the player and the game environment in plausible pre-computation and query times. Empirical proof of concept is shown based on an implementation in a tennis video game, where the IMPLANT agent is shown to exhibit a superior balance in adaptation performance and speed, when compared against other agent implementations.© 2009, Association for the Advancement of Artificial.
Source Title: Proceedings of the 5th Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE 2009
URI: http://scholarbank.nus.edu.sg/handle/10635/78180
ISBN: 9781577354314
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

46
checked on Nov 2, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.