paper-with-me

홈 › Papers

Boltzmann State-Dependent Rationality

2024-04-26 · Osher Lerner

This paper expands on existing learned models of human behavior via a measured step in structured irrationality. Specifically, by replacing the suboptimality constant $\beta$ in a Boltzmann rationality model with a function over states $\beta(s)$, we gain natural expressivity in a computationally tractable manner. This paper discusses relevant mathematical theory, sets up several experimental designs, presents limited preliminary results, and proposes future investigations.

📄 PDF Abstract BibTeX arXiv:2404.17725

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mitigating Cognitive Bias in RLHF by Altering Rationality

2026-05-07 · Tiffany Horter, Andrew Markham, Niki Trigoni, Serena Booth arxiv

How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outputs are used to train a reward model that assigns scalar values to re…

Reinforcement Learning

The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

2022-04-22 · ICLR 2022 4 · Cassidy Laidlaw, Anca Dragan

Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for…

Bayesian InferenceImitation Learning

Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

2010-12-01 · NeurIPS 2010 12 · George Dahl, Marc'Aurelio Ranzato, Abdel-rahman Mohamed, Geoffrey E. Hinton

Straightforward application of Deep Belief Nets (DBNs) to acoustic modeling produces a rich distributed representation of speech data that is useful for recognition and yields impressive results on the speaker-independen…

Scalable Equilibrium Sampling with Sequential Boltzmann Generators

2025-02-25 · Charlie B. Tan, Avishek Joey Bose, Chen Lin, Leon Klein 외

Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators tackle this problem by pairing powerful normalizing flows with importance sampl…

Boltzmann Generators -- Sampling Equilibrium States of Many-Body Systems with Deep Learning

2018-12-04 · Frank Noé, Simon Olsson, Jonas Köhler, Hao Wu

Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge. Lacking methods for generating statistically independent equilibrium samples in "one shot", vas…