@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
@article{JAAMAS13-chakrado,
  author = {Doran Chakraborty and Peter Stone},
  title = {Multiagent Learning in the Presence of Memory-Bounded Agents},
  journal = {Autonomous Agents and Multiagent Systems (JAAMAS)},
  year = {2013},
  publisher = {Springer},
  abstract = {
              In recent years, great strides have been made towards
              creating autonomous agents that can learn via
              interaction with their environment.  When considering
              just an individual agent, it is often appropriate to
              model the world as being stationary, meaning that the
              same action from the same state will always yield the
              same (possibly stochastic) effects.  However, in the
              presence of other independent agents, the environment is
              not stationary: an action's effects may depend on the
              actions of the other agents.  This non-stationarity
              poses the primary challenge of Multiagent Learning and
              comprises the main reason that it is best considered
              distinctly from single agent learning.
              The Multiagent Learning problem is often studied in the
              stylized settings provided by repeated matrix games. The
              goal of this article is to introduce a novel Multiagent
              Learning algorithm for such a setting, called
              Convergence with Model Learning and Safety (CMLES), that
              achieves a new set of objectives which have not been
              previously achieved. Specifically, CMLES is the first
              Multiagent Learning algorithm to achieve the following
              three objectives: (1) converges to following a Nash
              equilibrium joint-policy in self-play; (2) achieves
              close to the best response when interacting with a set
              of memory-bounded agents whose memory size is upper
              bounded by a known value; and (3) ensures an individual
              return that is very close to its security value when
              interacting with any other set of agents. Our
              presentation of CMLES is backed by a rigorous
              theoretical analysis, including an analysis of sample
              complexity wherever applicable.
  },
}