Boltzmann State-Dependent Rationality
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mitigating Cognitive Bias in RLHF by Altering Rationality
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 LearningThe Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models
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 LearningPhone Recognition with the Mean-Covariance Restricted Boltzmann Machine
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
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
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…