Introduces ERRL-ZSSDGs with coupled HJBI equations from DPP, semi-analytical LQ solutions via ODEs, and Actor-Critic approximation for general regime-switching jump-diffusion cases, illustrated on an investment game.
Journal of Machine Learning Research23(154), 1–55 (2022)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process
Introduces ERRL-ZSSDGs with coupled HJBI equations from DPP, semi-analytical LQ solutions via ODEs, and Actor-Critic approximation for general regime-switching jump-diffusion cases, illustrated on an investment game.