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

  title={Reinforcement learning, efficient coding, and the statistics of natural tasks},
  author={M. Botvinick and A. Weinstein and Alec Solway and A. Barto},
  journal={Current Opinion in Behavioral Sciences},
  • M. Botvinick, A. Weinstein, +1 author A. Barto
  • Published 2015
  • Computer Science
  • Current Opinion in Behavioral Sciences
  • 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
    30 Citations

    Figures and Topics from this paper

    Deep Reinforcement Learning and Its Neuroscientific Implications
    • 13
    • PDF
    Reinforcement Learning, Fast and Slow
    • 143
    Prefrontal Cortex as a Meta-Reinforcement Learning System
    • 2
    • PDF
    Computational evidence for hierarchically structured reinforcement learning in humans
    • PDF
    Prefrontal cortex as a meta-reinforcement learning system
    • 199
    • PDF
    Learning and transfer of working memory gating policies
    • 18
    • PDF


    Reinforcement Learning in Multidimensional Environments Relies on Attention Mechanisms
    • 191
    • PDF
    The structure of reinforcement-learning mechanisms in the human brain
    • 52
    Learning latent structure: carving nature at its joints
    • 190
    • PDF
    Generalization of value in reinforcement learning by humans
    • 87
    • PDF
    Human-level control through deep reinforcement learning
    • 11,349
    • PDF
    Natural image statistics and neural representation.
    • 1,982
    • PDF
    Eye movements in natural behavior
    • 1,035
    • PDF
    Structure learning in action
    • 151
    • PDF
    A Neural Substrate of Prediction and Reward
    • 6,794
    • PDF
    Recent Advances in Hierarchical Reinforcement Learning
    • 425