@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{BRACIS2019-Leno,
  author={Felipe Leno Da Silva and Anna Helena Reali Costa and Peter Stone},
  title={Building Self-Play Curricula Online by Playing with Expert Agents in Adversarial Games},
  booktitle={Proceedings of the 8th Brazilian Conference on Intelligent Systems (BRACIS)},
  location={Salvador, Bahia, Brazil},
  year={2019},
  abstract={Multiagent reinforcement learning algorithms are designed to enable an autonomous
   agent to adapt to an opponent's strategy based on experience.  However, most 
   such algorithms require a relatively large amount of experience to perform well.
    This requirement is problematic when opponent interactions are expensive, for 
    example, when the agent has limited access to the opponent during training. 
    In order to make good use of the opponent as a resource to support learning, 
    we propose SElf-PLay by Expert Modeling (SEPLEM), an algorithm that models the
     opponent policy in a few episodes, and uses it to train in a simulated 
     environment where it is cheaper to perform learning steps than in the real 
     environment. Our empirical evaluation indicates that SEPLEM, by iteratively 
     building a Curriculum of simulated tasks, achieves better performance than 
     both only playing against the expert and using pure Self-Play techniques. 
     SEPLEM is a promising technique to accelerate learning in multiagent 
     adversarial tasks. 
},
month = {October}
}