Robust Risk-Aware Reinforcement Learning

Understand

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.