paper-with-me

Papers

Two steps to risk sensitivity

2021-11-12 · NeurIPS 2021 12 · Chris Gagne, Peter Dayan

Distributional reinforcement learning (RL) -- in which agents learn about all the possible long-term consequences of their actions, and not just the expected value -- is of great recent interest. One of the most important affordances of a distributional view is facilitating a modern, measured, approach to risk when outcomes are not completely certain. By contrast, psychological and neuroscientific investigations into decision making under risk have utilized a variety of more venerable theoretical models such as prospect theory that lack axiomatically desirable properties such as coherence. Here, we consider a particularly relevant risk measure for modeling human and animal planning, called conditional value-at-risk (CVaR), which quantifies worst-case outcomes (e.g., vehicle accidents or predation). We first adopt a conventional distributional approach to CVaR in a sequential setting and reanalyze the choices of human decision-makers in the well-known two-step task, revealing substantial risk aversion that had been lurking under stickiness and perseveration. We then consider a further critical property of risk sensitivity, namely time consistency, showing alternatives to this form of CVaR that enjoy this desirable characteristic. We use simulations to examine settings in which the various forms differ in ways that have implications for human and animal planning and behavior.

📄 PDF Abstract BibTeX arXiv:2111.06803

Code (1)

crgagne/twosteps_neurips2021 공식 구현

Tasks

Decision MakingDistributional Reinforcement LearningReinforcement Learning (RL)SensitivityVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers

2026-05-11 · Chenyu Zhang arxiv

The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards w…

Image Generation

Empirical Risk Minimization with Relative Entropy Regularization: Optimality and Sensitivity Analysis

2022-02-09 · Samir M. Perlaza, Gaetan Bisson, Iñaki Esnaola, Alain Jean-Marie 외

The optimality and sensitivity of the empirical risk minimization problem with relative entropy regularization (ERM-RER) are investigated for the case in which the reference is a sigma-finite measure instead of a probabi…

Sensitivity

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

2026-02-27 · Yasaman Haghighi, Alexandre Alahi arxiv

Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerati…

Video Generation

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret

2020-06-22 · NeurIPS 2020 12 · Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang 외

We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels, where the goal is to optimize the total reward under the risk measure of exponential utility. We propo…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Robust Federated Learning with Global Sensitivity Estimation for Financial Risk Management

2025-02-24 · Lei Zhao, Lin Cai, Wu-Sheng Lu

In decentralized financial systems, robust and efficient Federated Learning (FL) is promising to handle diverse client environments and ensure resilience to systemic risks. We propose Federated Risk-Aware Learning with C…

Decision MakingFederated LearningManagementSensitivity