Accelerating Reinforcement Learning through Implicit Imitation

@article{Boutilier2003AcceleratingRL,
  title={Accelerating Reinforcement Learning through Implicit Imitation},
  author={Craig Boutilier and Bob Price},
  journal={J. Artif. Intell. Res.},
  year={2003},
  volume={19},
  pages={569-629}
}
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent’s ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative teachers or other more experienced agents. We propose and study a formal model of implicit imitation that can accelerate reinforcement learning dramatically in certain cases. Roughly, by observing a mentor, a reinforcement-learning agent can extract information… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 130 CITATIONS, ESTIMATED 21% COVERAGE

Beyond Rewards : Learning from Richer Supervision

K.V.N. PRADYOT, Thesis Certificate
  • 2011
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Requirements on the Use of Goal-Directed Imitation for Self-Adaptation

  • 17th International Workshop on Database and Expert Systems Applications (DEXA'06)
  • 2006
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2019

CITATION STATISTICS

  • 3 Highly Influenced Citations

  • Averaged 5 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 67 REFERENCES

Learning to fly.

  • Nursing times
  • 1998
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Complexity analysis of cooperative mechanisms in reinforcement learning

S. D. Whitehead
  • Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 607–613 Anaheim.
  • 1991
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Intelligent Social Learning

  • J. Artificial Societies and Social Simulation
  • 2001
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…