Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning
Publication:6143823
DOI10.1137/22m1527209arXiv2206.14666MaRDI QIDQ6143823
Álvaro Cartea, Unnamed Author, Sebastian Jaimungal
Publication date: 5 January 2024
Published in: SIAM Journal on Financial Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2206.14666
reinforcement learningtime-consistencyactor-critic algorithmelicitabilitydynamic risk measuresportfolio allocationstatistical arbitrageconsistent scoring functions
Statistical methods; risk measures (91G70) Reasoning under uncertainty in the context of artificial intelligence (68T37) Stochastic learning and adaptive control (93E35) Computational methods for problems pertaining to game theory, economics, and finance (91-08) Portfolio theory (91G10)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Making and Evaluating Point Forecasts
- Higher order elicitability and Osband's principle
- Eliciting production possibilities from a well-informed manager
- Risk-averse dynamic programming for Markov decision processes
- Joint generalized quantile and conditional tail expectation regression for insurance risk analysis
- On the elicitability of range value at risk
- Reinforcement learning and stochastic optimisation
- Convergence of the deep BSDE method for coupled FBSDEs
- Minimizing spectral risk measures applied to Markov decision processes
- Markov decision processes with recursive risk measures
- Dynamic coherent risk measures
- Deep quantile and deep composite triplet regression
- Coherent Measures of Risk
- Dynamic assessment indices
- COHERENCE AND ELICITABILITY
- Markov decision processes with iterated coherent risk measures
- Backward Stochastic Difference Equations and Nearly Time-Consistent Nonlinear Expectations
- Robustness and sensitivity analysis of risk measurement procedures
- Regression Quantiles
- Simulation-based optimization of Markov reward processes
- Robust Risk-Aware Reinforcement Learning
- Dynamic Risk Measures
- Sequential Decision Making With Coherent Risk
- Risk-Sensitive Reinforcement Learning
- Envelope Theorems for Arbitrary Choice Sets
- DISTRIBUTION‐INVARIANT RISK MEASURES, INFORMATION, AND DYNAMIC CONSISTENCY
- Elicitation of Personal Probabilities and Expectations
- Approximation by superpositions of a sigmoidal function
- Deep reinforcement learning for option pricing and hedging under dynamic expectile risk measures
- Sensitivity measures based on scoring functions
This page was built for publication: Conditionally Elicitable Dynamic Risk Measures for Deep Reinforcement Learning
