English
Related papers

Related papers: Entropy Regularized Belief Reporting

200 papers

Although pretrained language models (PTLMs) contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after specialized training. As a result, it can be hard to identify what…

Computation and Language · Computer Science 2021-10-01 Nora Kassner , Oyvind Tafjord , Hinrich Schütze , Peter Clark

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative…

Machine Learning · Computer Science 2026-01-08 Shijie Zhang , Kevin Zhang , Zheyuan Gu , Xiang Guo , Rujun Guo , Shaoyu Liu , Guanjun Jiang , Xiaozhao Wang

We examine how causal beliefs affect an agent's choices and how feedback on those choices leads to updated causal beliefs. Building on the structural-equations framework for modeling causality, we first examine the general problem of…

Theoretical Economics · Economics 2026-03-11 Joseph Y. Halpern , Evan Piermont , Marie-Louise Vierø

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with…

Machine Learning · Computer Science 2022-01-03 Tien Mai , Patrick Jaillet

We study an opinion formation model by the means of a co-evolving complex network where the vertices represent the individuals, characterised by their evolving opinions, and the edges represent the interactions among them. The network…

Physics and Society · Physics 2015-06-19 Enrique Burgos , Laura Hernandez , Horacio Ceva , Roberto P. J. Perazzo

Opinion formation models typically represent each individual as a single variable. However, in practice each individual holds interconnected beliefs whose internal organization may influence collective outcomes. To explore this dependence,…

Physics and Society · Physics 2026-05-21 Irene Ferri , Albert Díaz-Guilera , Hiroki Sayama

Safety-critical autonomy in adversarial settings demands more than Lyapunov stability of tracking error signals. An agent executing a goal-directed trajectory is intrinsically legible to a passive observer running online Bayesian inference,…

Systems and Control · Electrical Eng. & Systems 2026-05-08 Yixuan Wang , Dan Guralnik , Warren Dixon

Large language models (LLMs) are increasingly used as simulated participants in social science experiments, but their behavior is often unstable and highly sensitive to design choices. Prior evaluations frequently conflate base-model…

Artificial Intelligence · Computer Science 2026-02-03 Xuan Liu , Haoyang Shang , Zizhang Liu , Xinyan Liu , Yunze Xiao , Yiwen Tu , Haojian Jin

Autonomous agents powered by LLMs and Retrieval-Augmented Generation (RAG) are proficient consumers of digital content but remain unidirectional, a limitation we term epistemic asymmetry. This isolation leads to redundant reasoning and…

Artificial Intelligence · Computer Science 2025-12-25 Zan-Kai Chong , Hiroyuki Ohsaki , Bryan Ng

Interactive large language model (LLM) agents operating via multi-turn dialogue and multi-step tool calling are increasingly used in production. Benchmarks for these agents must both reliably compare models and yield on-policy training…

The BLP model is the workhorse framework in empirical IO and enables estimation of demand models for differentiated products using aggregate product shares. In practice, however, the share of the outside good is often unobserved. This paper…

Econometrics · Economics 2026-02-24 Federico A. Bugni , Joel L. Horowitz , Linqi Zhang

We show how to train the fast dependency parser of Smith and Eisner (2008) for improved accuracy. This parser can consider higher-order interactions among edges while retaining O(n^3) runtime. It outputs the parse with maximum expected…

Computation and Language · Computer Science 2015-08-11 Matthew R. Gormley , Mark Dredze , Jason Eisner

Entity-level unlearning is usually evaluated by what a model says: whether it stops naming the target, refuses a query, or shifts a Truth Ratio distribution. These output-level tests, however, do not show whether a subject's internal…

Mixture distributions are a workhorse model for multimodal data in information theory, signal processing, and machine learning. Yet even when each component density is simple, the differential entropy of the mixture is notoriously hard to…

Information Theory · Computer Science 2026-02-18 Namyoon Lee

Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stochastic policies for…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Zafarali Ahmed , Doina Precup

In this contribution, we propose a generic online (also sometimes called adaptive or recursive) version of the Expectation-Maximisation (EM) algorithm applicable to latent variable models of independent observations. Compared to the…

Computation · Statistics 2017-03-02 Olivier Cappé , Eric Moulines

We propose a model of unawareness that remains close to the paradigm of Aumann's model for knowledge [R. J. Aumann, International Journal of Game Theory 28 (1999) 263-300]: just as Aumann uses a correspondence on a state space to define an…

Theoretical Economics · Economics 2024-12-25 Wesley H. Holliday

The method of Maximum (relative) Entropy (ME) is used to translate the information contained in the known form of the likelihood into a prior distribution for Bayesian inference. The argument is guided by intuition gained from the…

Data Analysis, Statistics and Probability · Physics 2009-11-10 Ariel Caticha , Roland Preuss

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators…

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable,…

‹ Prev 1 8 9 10 Next ›