On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics

arXiv:2310.19527v2 Announce Type: replace
Abstract: Risk-aware Reinforcement Learning (RL) algorithms like SAC and TD3 were shown empirically to outperform their risk-neutral counterparts in a variety of continuous-action tasks. However, the theoretical basis for the pessimistic objectives these algorithms employ remains unestablished, raising questions about the specific class of policies they are implementing. In this work, we apply the expected utility hypothesis, a fundamental concept in economics, to illustrate that both risk-neutral and risk-aware RL goals can be interpreted through expected …

abstract actor actor-critic agents algorithms arxiv class continuous cs.lg economics questions reinforcement reinforcement learning risk tasks theory type