Robust Risk-Aware Reinforcement Learning
This work addresses robust risk management in reinforcement learning for financial domains, representing an incremental advancement by combining existing risk and robustness concepts.
The paper tackles the problem of robust optimization for risk-aware reinforcement learning by using rank dependent expected utility and worst-case distributions within a Wasserstein ball, resulting in explicit policy gradient formulae and demonstrated efficacy on three financial applications.
We present a reinforcement learning (RL) approach for robust optimisation of risk-aware performance criteria. To allow agents to express a wide variety of risk-reward profiles, we assess the value of a policy using rank dependent expected utility (RDEU). RDEU allows the agent to seek gains, while simultaneously protecting themselves against downside risk. To robustify optimal policies against model uncertainty, we assess a policy not by its distribution, but rather, by the worst possible distribution that lies within a Wasserstein ball around it. Thus, our problem formulation may be viewed as an actor/agent choosing a policy (the outer problem), and the adversary then acting to worsen the performance of that strategy (the inner problem). We develop explicit policy gradient formulae for the inner and outer problems, and show its efficacy on three prototypical financial problems: robust portfolio allocation, optimising a benchmark, and statistical arbitrage.