PMID- 27030803
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20240325
IS  - 1943-068X (Print)
IS  - 1943-0698 (Electronic)
IS  - 1943-068X (Linking)
VI  - 8
IP  - 1
DP  - 2016 Mar 12
TI  - Discovering Multimodal Behavior in Ms. Pac-Man through Evolution of Modular 
      Neural Networks.
PG  - 67-81
AB  - Ms. Pac-Man is a challenging video game in which multiple modes of behavior are 
      required: Ms. Pac-Man must escape ghosts when they are threats and catch them 
      when they are edible, in addition to eating all pills in each level. Past 
      approaches to learning behavior in Ms. Pac-Man have treated the game as a single 
      task to be learned using monolithic policy representations. In contrast, this 
      paper uses a framework called Modular Multi-objective NEAT (MM-NEAT) to evolve 
      modular neural networks. Each module defines a separate behavior. The modules are 
      used at different times according to a policy that can be human-designed (i.e. 
      Multitask) or discovered automatically by evolution. The appropriate number of 
      modules can be fixed or discovered using a genetic operator called Module 
      Mutation. Several versions of Module Mutation are evaluated in this paper. Both 
      fixed modular networks and Module Mutation networks outperform monolithic 
      networks and Multitask networks. Interestingly, the best networks dedicate 
      modules to critical behaviors (such as escaping when surrounded after luring 
      ghosts near a power pill) that do not follow the customary division of the game 
      into chasing edible and escaping threat ghosts. The results demonstrate that 
      MM-NEAT can discover interesting and effective behavior for agents in challenging 
      games.
FAU - Schrum, Jacob
AU  - Schrum J
AD  - Department of Mathematics and Computer Science, Southwestern University, 
      Georgetown, TX 78626 USA ( schrum2@southwestern.edu ).
FAU - Miikkulainen, Risto
AU  - Miikkulainen R
AD  - Department of Computer Science, University of Texas, Austin, TX, 78712 USA ( 
      risto@cs.utexas.edu ).
LA  - eng
GR  - R01 GM105042/GM/NIGMS NIH HHS/United States
PT  - Journal Article
PL  - United States
TA  - IEEE Trans Comput Intell AI Games
JT  - IEEE transactions on computational intelligence and AI in games
JID - 101659801
PMC - PMC4809543
MID - NIHMS694381
OTO - NOTNLM
OT  - Modularity
OT  - Ms. Pac-Man
OT  - Multimodal Behavior
OT  - Multiobjective Optimization
OT  - Neuroevolution
EDAT- 2016/04/01 06:00
MHDA- 2016/04/01 06:01
PMCR- 2016/03/28
CRDT- 2016/04/01 06:00
PHST- 2016/04/01 06:00 [entrez]
PHST- 2016/04/01 06:00 [pubmed]
PHST- 2016/04/01 06:01 [medline]
PHST- 2016/03/28 00:00 [pmc-release]
AID - 10.1109/TCIAIG.2015.2390615 [doi]
PST - ppublish
SO  - IEEE Trans Comput Intell AI Games. 2016 Mar 12;8(1):67-81. doi: 
      10.1109/TCIAIG.2015.2390615.