Discovering symbolic policies with deep reinforcement learning

Mikel Landajuela Larma, Brenden K. Petersen, Sookyung Kim, Cláudio P. Santiago, Ruben Glatt, T. Nathan Mundhenk, Jacob F. Pettit, Daniel M. Faissol

Abstract: Deep reinforcement learning (DRL) has proven successful for many difficult control problems by learning policies represented by neural networks. However, the complexity of neural network-based poli...