Ricerc@Sapienza

Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors. Numerical methods for curriculum learning in the literature provides only initial heuristic solutions, with little to no guarantee on their quality. We define a new gray-box function that, including a suitable scheduling problem, can be effectively used to reformulate the curriculum learning problem. We propose different efficient numerical methods to address this gray-box reformulation.

A trading strategy simply consists in a procedure which defines conditions for buying or selling a security on a financial market. These decisions rely on the values of some indicators that, in turn, affect the tuning of the strategy parameters. The choice of these parameters significantly affects the performance of the trading strategy.