论文标题
有条件地进行深入加强学习的有条理的动态风险措施
Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning
论文作者
论文摘要
我们提出了一个新型框架，以解决对风险敏感的增强学习（RL）问题，在该问题中，代理优化了时触时的动态光谱风险度量。基于条件启发性的概念，我们的方法构建（严格一致）评分函数在估计程序中用作惩罚者。 Our contribution is threefold: we (i) devise an efficient approach to estimate a class of dynamic spectral risk measures with deep neural networks, (ii) prove that these dynamic spectral risk measures may be approximated to any arbitrary accuracy using deep neural networks, and (iii) develop a risk-sensitive actor-critic algorithm that uses full episodes and does not require any additional nested transitions.我们将概念上改进的增强学习算法与嵌套模拟方法进行了比较，并在两个设置中说明了其性能：统计套证和模拟和真实数据的投资组合分配。
We propose a novel framework to solve risk-sensitive reinforcement learning (RL) problems where the agent optimises time-consistent dynamic spectral risk measures. Based on the notion of conditional elicitability, our methodology constructs (strictly consistent) scoring functions that are used as penalizers in the estimation procedure. Our contribution is threefold: we (i) devise an efficient approach to estimate a class of dynamic spectral risk measures with deep neural networks, (ii) prove that these dynamic spectral risk measures may be approximated to any arbitrary accuracy using deep neural networks, and (iii) develop a risk-sensitive actor-critic algorithm that uses full episodes and does not require any additional nested transitions. We compare our conceptually improved reinforcement learning algorithm with the nested simulation approach and illustrate its performance in two settings: statistical arbitrage and portfolio allocation on both simulated and real data.
