Estimating scale-invariant future in continuous time
This addresses the computational inefficiency and time-scale selection issues in existing reinforcement learning algorithms, offering a novel approach for natural learners and potential integration into future algorithms.
The paper tackles the problem of estimating future outcomes in continuous time for reinforcement learning, presenting a computational mechanism that efficiently computes a scale-invariant timeline of future outcomes on a logarithmically-compressed scale, enabling a power-law-discounted estimate of expected future reward in a single parallel operation.
Natural learners must compute an estimate of future outcomes that follow from a stimulus in continuous time. Widely used reinforcement learning algorithms discretize continuous time and estimate either transition functions from one step to the next (model-based algorithms) or a scalar value of exponentially-discounted future reward using the Bellman equation (model-free algorithms). An important drawback of model-based algorithms is that computational cost grows linearly with the amount of time to be simulated. On the other hand, an important drawback of model-free algorithms is the need to select a time-scale required for exponential discounting. We present a computational mechanism, developed based on work in psychology and neuroscience, for computing a scale-invariant timeline of future outcomes. This mechanism efficiently computes an estimate of inputs as a function of future time on a logarithmically-compressed scale, and can be used to generate a scale-invariant power-law-discounted estimate of expected future reward. The representation of future time retains information about what will happen when. The entire timeline can be constructed in a single parallel operation which generates concrete behavioral and neural predictions. This computational mechanism could be incorporated into future reinforcement learning algorithms.