Meta-learning in Reinforcement Learning

@article{Schweighofer2003MetalearningIR,
  title={Meta-learning in Reinforcement Learning},
  author={Nicolas Schweighofer and Kenji Doya},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2003},
  volume={16 1},
  pages={
          5-9
        }
}
Meta-parameters in reinforcement learning should be tuned to the environmental dynamics and the animal performance. Here, we propose a biologically plausible meta-reinforcement learning algorithm for tuning these meta-parameters in a dynamic, adaptive manner. We tested our algorithm in both a simulation of a Markov decision task and in a non-linear control task. Our results show that the algorithm robustly finds appropriate meta-parameter values, and controls the meta-parameter time course, in… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 89 CITATIONS, ESTIMATED 73% COVERAGE

Dopamine blockade impairs the exploration-exploitation trade-off in rats

  • Scientific Reports
  • 2019
VIEW 10 EXCERPTS
CITES BACKGROUND & RESULTS
HIGHLY INFLUENCED

Active Exploration and Parameterized Reinforcement Learning Applied to a Simulated Human-Robot Interaction Task

  • 2017 First IEEE International Conference on Robotic Computing (IRC)
  • 2017
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Bio-inspired meta-learning for active exploration during non-stationary multi-armed bandit tasks

  • 2017 Intelligent Systems Conference (IntelliSys)
  • 2017
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2004
2019

CITATION STATISTICS

  • 12 Highly Influenced Citations

  • Averaged 11 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Functional MRI study of short-term and long-term prediction of reward

S. Tanaka, K. Doya, +3 authors S. Yamawaki
  • Proceedings of the Eighth International Conference on Functional Mapping of the Human Brain, Sendai,
  • 2002
VIEW 1 EXCERPT

Metalearning and neuromodulation

  • Neural Networks
  • 2002
VIEW 2 EXCERPTS

Predictive reward signal of dopamine neurons.

  • Journal of neurophysiology
  • 1998
VIEW 1 EXCERPT

On the complexity of solving Markov decision problems

M. L. Littman, Dean, L T.
  • Eleventh International Conference on Uncertainty in Artificial Intelligence
  • 1995
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…