2018

Safe Exploration in Continuous Action Spaces

Dalal, Gal, Dvijotham, Krishnamurthy, Vecerik, Matej et al.

Understand

We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated.

  • We show how to exploit the typically smooth dynamics of these systems and enable RL algorithms to never violate constraints during learning.
  • Our technique is to directly add to the policy a safety layer that analytically solves an action correction formulation per each state.
  • The novelty of obtaining an elegant closed-form solution is attained due to a linearized model, learned on past trajectories consisting of arbitrary actions.

Reading the bibliography…