A policy gradient approach for optimization of smooth risk measures
This addresses risk management in RL for applications like finance or robotics, but it is incremental as it extends existing policy gradient methods to risk measures.
The paper tackles the problem of optimizing risk-sensitive reinforcement learning by proposing policy gradient algorithms for smooth risk measures, achieving non-asymptotic convergence bounds to stationary points.
We propose policy gradient algorithms for solving a risk-sensitive reinforcement learning (RL) problem in on-policy as well as off-policy settings. We consider episodic Markov decision processes, and model the risk using the broad class of smooth risk measures of the cumulative discounted reward. We propose two template policy gradient algorithms that optimize a smooth risk measure in on-policy and off-policy RL settings, respectively. We derive non-asymptotic bounds that quantify the rate of convergence of our proposed algorithms to a stationary point of the smooth risk measure. As special cases, we establish that our algorithms apply to optimization of mean-variance and distortion risk measures, respectively.