Smoothing Policies and Safe Policy Gradients. (arXiv:1905.03231v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/1905.03231

Policy Gradient (PG) algorithms are among the best candidates for the
much-anticipated applications of reinforcement learning to real-world control
tasks, such as robotics. However, the trial-and-error nature of these methods
poses safety issues whenever the learning process itself must be performed on a
physical system or involves any form of human-computer interaction. In this
paper, we address a specific safety formulation, where both goals and dangers
are encoded in a scalar reward signal and the learning agent is constrained to …

arxiv lg policy