Explore/Exploit Strategies in Autonomy

@inproceedings{Maes1996ExploreExploitSI,
  title={Explore/Exploit Strategies in Autonomy},
  author={Pattie Maes and Maja J. Mataric and Jean-Arcady Meyer and Jordan B. Pollack and Stewart W. Wilson},
  year={1996}
}
In this paper, reinforcement learning algorithms are applied to a foraging task, expressed as a control composition problem. The domain used is a simulated world in which a variety of creatures (agents) live and interact, reacting to stimuli and to each other. In such dynamic, uncertain environments, fast adaptation is important, and there is a need for new architectures that facilitate online learning. Recently, control composition has shown its potential in reducing the complexity of learning… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 45 CITATIONS

The Exploration-Exploitation Dilemma for Adaptive Agents

VIEW 4 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Evolving Optimal Populations with XCS Classi

  • er SystemsTim KovacsOctober
  • 1996
VIEW 31 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

The Neural Mind and the Robot

VIEW 1 EXCERPT
CITES BACKGROUND

Video Game AI Algorithms

VIEW 1 EXCERPT
CITES BACKGROUND

Effects of Dynamic Goals on Agent Performance

VIEW 1 EXCERPT
CITES BACKGROUND