Reinforcement learning, efficient coding, and the statistics of natural tasks

@article{Botvinick2015ReinforcementLE,
  title={Reinforcement learning, efficient coding, and the statistics of natural tasks},
  author={Matthew M Botvinick and Ari Weinstein and Alec Solway and Andrew G. Barto},
  journal={Current Opinion in Behavioral Sciences},
  year={2015},
  volume={5},
  pages={71-77}
}
The application of ideas from computational reinforcement learning has recently enabled dramatic advances in behavioral and neuroscientific research. For the most part, these advances have involved insights concerning the algorithms underlying learning and decision making. In the present article, we call attention to the equally important but relatively neglected question of how problems in learning and decision making are internally represented. To articulate the significance of representation… CONTINUE READING
6
Twitter Mentions

Figures and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 15 CITATIONS

Reinforcement Learning, Fast and Slow

VIEW 1 EXCERPT
CITES BACKGROUND

Towards a Definition of Disentangled Representations

VIEW 1 EXCERPT
CITES BACKGROUND

Towards learning-to-learn

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 71 REFERENCES

Interplay of approximate planning strategies.

VIEW 1 EXCERPT

Reinforcement learning in multidimensional environments relies on attention mechanisms.

VIEW 2 EXCERPTS

Sparse encoding of complex action sequences

  • WW Abbott, AA Thomik, AA Faisal
  • Cosyne ( computational and systems neuroscience )
  • 2015

Sparse encoding of complex action sequences. Cosyne (computational and systems neuroscience)

  • WW Abbott, AA Thomik, AA Faisal
  • 2015