paper-with-me

Papers

Soft Q-Learning with Mutual-Information Regularization

2019-05-01 · ICLR 2019 5 · Jordi Grau-Moya, Felix Leibfried, Peter Vrancx

We propose a reinforcement learning (RL) algorithm that uses mutual-information regularization to optimize a prior action distribution for better performance and exploration. Entropy-based regularization has previously been shown to improve both exploration and robustness in challenging sequential decision-making tasks. It does so by encouraging policies to put probability mass on all actions. However, entropy regularization might be undesirable when actions have significantly different importance. In this paper, we propose a theoretically motivated framework that dynamically weights the importance of actions by using the mutual-information. In particular, we express the RL problem as an inference problem where the prior probability distribution over actions is subject to optimization. We show that the prior optimization introduces a mutual-information regularizer in the RL objective. This regularizer encourages the policy to be close to a non-uniform distribution that assigns higher probability mass to more important actions. We empirically demonstrate that our method significantly improves over entropy regularization methods and unregularized methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingQ-LearningReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음

Similar Papers 제목 키워드 기반

Mutual-Information Regularization in Markov Decision Processes and Actor-Critic Learning

2019-09-11 · Felix Leibfried, Jordi Grau-Moya

Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent to enforcing small deviations from a uni…

MuJoCoQ-LearningReinforcement LearningReinforcement Learning (RL)

SMoES: Soft Modality-Guided Expert Specialization in MoE-VLMs

2026-04-27 · Zi-Hao Bo, Yaqian Li, Anzhou Hou, Rinyoichi Takezoe 외 arxiv

Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are eith…

Deep clustering: On the link between discriminative models and K-means

2018-10-09 · Mohammed Jabi, Marco Pedersoli, Amar Mitiche, Ismail Ben Ayed

In the context of recent deep clustering studies, discriminative models dominate the literature and report the most competitive performances. These models learn a deep discriminative neural network classifier in which th…

ClusteringDeep ClusteringImage Clusteringregression

Neural Network Classifier as Mutual Information Evaluator

2021-06-19 · Zhenyue Qin, Dongwoo Kim, Tom Gedeon

Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators. We show t…

Form

Hierarchical Soft Actor-Critic: Adversarial Exploration via Mutual Information Optimization

2019-06-17 · Ari Azarafrooz, John Brock

We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations…