English
Related papers

Related papers: A Mutual Information-based Metric for Temporal Exp…

200 papers

Continual Instruction Tuning (CIT) is adopted to continually instruct Large Models to follow human intent data by data. It is observed that existing gradient update would heavily destroy the performance on previous datasets during CIT…

Machine Learning · Computer Science 2025-12-15 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Yanyun Qu , Shouhong Ding , Yuan Xie

This paper develops the first policy gradient method with global optimality guarantee and complexity analysis for robust reinforcement learning under model mismatch. Robust reinforcement learning is to learn a policy robust to model…

Machine Learning · Computer Science 2022-05-17 Yue Wang , Shaofeng Zou

We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate…

Machine Learning · Computer Science 2021-12-06 Hung Le , Majid Abdolshah , Thommen K. George , Kien Do , Dung Nguyen , Svetha Venkatesh

We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across…

Optimization and Control · Mathematics 2024-05-01 Robert Denkert , Huyên Pham , Xavier Warin

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…

Machine Learning · Computer Science 2023-03-27 Jongheon Jeong , Sihyun Yu , Hankook Lee , Jinwoo Shin

All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…

Machine Learning · Computer Science 2018-04-05 Trevor Barron , Oliver Obst , Heni Ben Amor

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We…

Artificial Intelligence · Computer Science 2016-12-06 Pierre-Luc Bacon , Jean Harb , Doina Precup

Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks. This paper presents an information-theoretic bound on the…

Machine Learning · Computer Science 2021-02-09 Arezou Rezazadeh , Sharu Theresa Jose , Giuseppe Durisi , Osvaldo Simeone

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

We study the problem of temporal-difference-based policy evaluation in reinforcement learning. In particular, we analyse the use of a distributional reinforcement learning algorithm, quantile temporal-difference learning (QTD), for this…

Machine Learning · Computer Science 2023-05-31 Mark Rowland , Yunhao Tang , Clare Lyle , Rémi Munos , Marc G. Bellemare , Will Dabney

Representations learned by self-supervised approaches are generally considered to possess sufficient generalizability and discriminability. However, we disclose a nontrivial mutual-exclusion relationship between these critical…

Artificial Intelligence · Computer Science 2024-12-03 Jiangmeng Li , Zehua Zang , Qirui Ji , Chuxiong Sun , Wenwen Qiang , Junge Zhang , Changwen Zheng , Fuchun Sun , Hui Xiong

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively…

There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpretability of reinforcement learning by increasing the utility…

Machine Learning · Computer Science 2019-07-03 Aaron M. Roth , Nicholay Topin , Pooyan Jamshidi , Manuela Veloso

Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems. However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm. Hence,…

Machine Learning · Computer Science 2019-09-10 James O' Neill , Danushka Bollegala

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate…

Machine Learning · Computer Science 2020-01-24 Michael Tschannen , Josip Djolonga , Paul K. Rubenstein , Sylvain Gelly , Mario Lucic

Mutual information maximization provides an appealing formalism for learning representations of data. In the context of reinforcement learning (RL), such representations can accelerate learning by discarding irrelevant and redundant…

Machine Learning · Computer Science 2021-06-15 Kate Rakelly , Abhishek Gupta , Carlos Florensa , Sergey Levine

Multi-agent reinforcement learning in mixed-motive settings presents a fundamental challenge: agents must balance individual interests with collective goals, which are neither fully aligned nor strictly opposed. To address this, reward…

Multiagent Systems · Computer Science 2025-08-26 Woojun Kim , Katia Sycara

Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly development work of preparing vast amounts of task-matched transcribed…

Computation and Language · Computer Science 2017-11-13 Taku Kato , Takahiro Shinozaki

Quantum tangent kernel methods provide an efficient approach to analyzing the performance of quantum machine learning models in the infinite-width limit, which is of crucial importance in designing appropriate circuit architectures for…

Quantum Physics · Physics 2023-11-10 Li-Wei Yu , Weikang Li , Qi Ye , Zhide Lu , Zizhao Han , Dong-Ling Deng