arXiv subjects

Hyejin Ku

Publications and source records attributed to Hyejin Ku.

4 recordsLinked to original sources

arXiv2026

Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting

Distributional reinforcement learning (RL) is a powerful framework increasingly adopted in safety-critical domains for its ability to optimize risk-sensitive objectives. However, the role of the discount factor is often overlooked, as it is typically treated as a fixed parameter of the Markov decision process or tunable hyperparameter, with little consideration of its effect on the learned policy. In the literature, it is well-known that the discounting function plays a major role in characterizing time preferences of an agent, which an exponential discount factor cannot fully capture. Building on this insight, we propose a novel framework that supports flexible discounting of future rewards and optimization of risk measures in distributional RL. We provide a technical analysis of the optimality of our algorithms, show that our multi-horizon extension fixes issues raised with existing methodologies, and validate the robustness of our methods through extensive experiments. Our results highlight that discounting is a cornerstone in decision-making problems for capturing more expressive temporal and risk preferences profiles, with potential implications for real-world safety-critical applications.

cs.LG↗

arXiv2025

Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning

The development of Distributional Reinforcement Learning (DRL) has introduced a natural way to incorporate risk sensitivity into value-based and actor-critic methods by employing risk measures other than expectation in the value function. While this approach is widely adopted in many online and offline RL algorithms due to its simplicity, the naive integration of risk measures often results in suboptimal policies. This limitation can be particularly harmful in scenarios where the need for effective risk-sensitive policies is critical and worst-case outcomes carry severe consequences. To address this challenge, we propose a novel framework for optimizing static Spectral Risk Measures (SRM), a flexible family of risk measures that generalizes objectives such as CVaR and Mean-CVaR, and enables the tailoring of risk preferences. Our method is applicable to both online and offline RL algorithms. We establish theoretical guarantees by proving convergence in the finite state-action setting. Moreover, through extensive empirical evaluations, we demonstrate that our algorithms consistently outperform existing risk-sensitive methods in both online and offline environments across diverse domains.

cs.LG↗

arXiv2025

Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning

In domains such as finance, healthcare, and robotics, managing worst-case scenarios is critical, as failure to do so can lead to catastrophic outcomes. Distributional Reinforcement Learning (DRL) provides a natural framework to incorporate risk sensitivity into decision-making processes. However, existing approaches face two key limitations: (1) the use of fixed risk measures at each decision step often results in overly conservative policies, and (2) the interpretation and theoretical properties of the learned policies remain unclear. While optimizing a static risk measure addresses these issues, its use in the DRL framework has been limited to the simple static CVaR risk measure. In this paper, we present a novel DRL algorithm with convergence guarantees that optimizes for a broader class of static Spectral Risk Measures (SRM). Additionally, we provide a clear interpretation of the learned policy by leveraging the distribution of returns in DRL and the decomposition of static coherent risk measures. Extensive experiments demonstrate that our model learns policies aligned with the SRM objective, and outperforms existing risk-neutral and risk-sensitive DRL models in various settings.

cs.LG↗

arXiv2024

Causal Duration Analysis with Diff-in-Diff

In economic program evaluation, it is common to obtain panel data in which outcomes are indicators that an individual has reached an absorbing state. For example, they may indicate whether an individual has exited a period of unemployment, passed an exam, left a marriage, or had their parole revoked. The parallel trends assumption that underpins difference-in-differences generally fails in such settings. We suggest identifying conditions similar to those of difference-in-differences, but which apply to hazard rates rather than mean outcomes. These alternative assumptions motivate estimators that retain the simplicity and transparency of standard diff-in-diff, and corresponding specification tests. Our approach can be adapted to include general linear restrictions between the hazard rates of different groups, motivating duration analogues of the triple differences and synthetic control methods. We apply our procedures to examine the impact of a policy that increased the generosity of unemployment benefits, using a cross-cohort comparison.

econ.EM↗