Exploration and apprenticeship learning in reinforcement learning

@inproceedings{Abbeel2005ExplorationAA,
  title={Exploration and apprenticeship learning in reinforcement learning},
  author={Pieter Abbeel and Andrew Y. Ng},
  booktitle={ICML},
  year={2005}
}
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies" to drive the system towards poorly modeled states, so as to encourage exploration. But this makes these algorithms impractical for many systems; for example, on an autonomous helicopter, overly aggressive exploration may well result in a crash. In this paper, we consider the apprenticeship learning setting in which a… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 171 CITATIONS, ESTIMATED 23% COVERAGE

Safe and Interactive Autonomy: Control, Learning, and Verification

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Integrating learning by experience and demonstration in autonomous robots

  • Adaptive Behaviour
  • 2015
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Agnostic System Identification for Model-Based Reinforcement Learning

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Autonomous Helicopter Aerobatics through Apprenticeship Learning

  • I. J. Robotics Res.
  • 2010
VIEW 8 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

A unifying framework for computational reinforcement learning theory

VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

A Game-Theoretic Approach to Apprenticeship Learning — Supplement

VIEW 4 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2019

CITATION STATISTICS

  • 20 Highly Influenced Citations

  • Averaged 15 Citations per year over the last 3 years

  • 30% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-4 OF 4 REFERENCES

Similar Papers

Loading similar papers…