Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning

by   Anthony Coache, et al.

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.


page 19

page 23


Reinforcement Learning with Dynamic Convex Risk Measures

We develop an approach for solving time-consistent risk-sensitive stocha...

Policy Gradient for Coherent Risk Measures

Several authors have recently developed risk-sensitive policy gradient m...

Practical Risk Measures in Reinforcement Learning

Practical application of Reinforcement Learning (RL) often involves risk...

Deep Reinforcement Learning for Equal Risk Pricing and Hedging under Dynamic Expectile Risk Measures

Recently equal risk pricing, a framework for fair derivative pricing, wa...

Lyapunov-Based Reinforcement Learning State Estimator

In this paper, we consider the state estimation problem for nonlinear st...

A Natural Actor-Critic Algorithm with Downside Risk Constraints

Existing work on risk-sensitive reinforcement learning - both for symmet...

Neural-Progressive Hedging: Enforcing Constraints in Reinforcement Learning with Stochastic Programming

We propose a framework, called neural-progressive hedging (NP), that lev...

Please sign up or login with your details

Forgot password? Click here to reset