Infoscience

Report

Estimates of Parameter Distributions for Optimal Action Selection

We present a general method for maintaining estimates of the distribution of parameters in arbitrary models. This is then applied to the estimation of probability distribution over actions in value-based reinforcement learning. While this approach is similar to other techniques that maintain a confidence measure for action-values, it nevertheless offers a new insight into current techniques and reveals potential avenues of further research.

Fulltext

  • There is no available fulltext. Please contact the lab or the authors.

Related material

Contacts

EPFL authors