From competition to cooperation: Co-evolution in a rewards continuum.
Daniel A. AshlockWendy AshlockSpyridon SamothrakisSimon M. LucasColin LeePublished in: CIG (2012)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- markov decision processes
- real time
- evolutionary game theory
- artificial intelligence
- multi agent systems
- data sets
- long term and short term
- temporal evolution
- expert systems
- data structure
- real world
- web services
- computational complexity
- website
- social networks
- information retrieval
- free riding
- bandit problems
- multiarmed bandit
- neural network
- human agent interaction