English
Related papers

Related papers: Augmenting Replay in World Models for Continual Re…

200 papers

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data…

Machine Learning · Computer Science 2023-03-08 Stella Ho , Ming Liu , Lan Du , Longxiang Gao , Yong Xiang

User behavior on online platforms is evolving, reflecting real-world changes in how people post, whether it's helpful messages or hate speech. Models that learn to capture this content can experience a decrease in performance over time due…

Machine Learning · Computer Science 2025-11-04 Yasas Senarath , Hemant Purohit

Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is catastrophic forgetting, a phenomenon in which a model…

Machine Learning · Computer Science 2025-02-18 Andrii Krutsylo

Nearly all real world tasks are inherently partially observable, necessitating the use of memory in Reinforcement Learning (RL). Most model-free approaches summarize the trajectory into a latent Markov state using memory models borrowed…

Machine Learning · Computer Science 2023-10-09 Steven Morad , Ryan Kortvelesy , Stephan Liwicki , Amanda Prorok

Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet remains limited by low sample efficiency, stemming not only from sparse outcome feedback but also from the agent's inability to leverage prior…

Machine Learning · Computer Science 2026-03-19 Dilxat Muhtar , Jiashun Liu , Wei Gao , Weixun Wang , Shaopan Xiong , Ju Huang , Siran Yang , Wenbo Su , Jiamang Wang , Ling Pan , Bo Zheng

We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms…

Machine Learning · Computer Science 2019-09-18 Hado van Hasselt , Matteo Hessel , John Aslanides

Fictitious play with reinforcement learning is a general and effective framework for zero-sum games. However, using the current deep neural network models, the implementation of fictitious play faces crucial challenges. Neural network model…

Machine Learning · Computer Science 2019-12-02 Rong-Jun Qin , Jing-Cheng Pang , Yang Yu

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

Artificial Intelligence · Computer Science 2025-02-25 Zhao Yang , Thomas M. Moerland , Mike Preuss , Aske Plaat , Edward S. Hu

In recent years, $Q$-learning has become indispensable for model-free reinforcement learning (MFRL). However, it suffers from well-known problems such as under- and overestimation bias of the value, which may adversely affect the policy…

Machine Learning · Computer Science 2021-02-09 Youngmin Oh , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our…

Machine Learning · Computer Science 2022-04-22 Cinjon Resnick , Roberta Raileanu , Sanyam Kapoor , Alexander Peysakhovich , Kyunghyun Cho , Joan Bruna

Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is severely hindered by inefficient credit assignment in long-horizon tasks and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Han Xiao , Guozhi Wang , Hao Wang , Shilong Liu , Yuxiang Chai , Yue Pan , Yufeng Zhou , Xiaoxin Chen , Yafei Wen , Hongsheng Li

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

Machine Learning · Computer Science 2024-06-06 Minting Pan , Yitao Zheng , Yunbo Wang , Xiaokang Yang

Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for…

Machine Learning · Computer Science 2019-01-08 Vikas Dhiman , Shurjo Banerjee , Jeffrey M. Siskind , Jason J. Corso

A central component of training in Reinforcement Learning (RL) is Experience: the data used for training. The mechanisms used to generate and consume this data have an important effect on the performance of RL algorithms. In this paper, we…

Machine Learning · Computer Science 2021-02-10 Albin Cassirer , Gabriel Barth-Maron , Eugene Brevdo , Sabela Ramos , Toby Boyd , Thibault Sottiaux , Manuel Kroiss

Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often…

Machine Learning · Computer Science 2022-02-18 Yizhi Yuan , Marcelo G Mattar

Missing modalities consistently lead to significant performance degradation in multimodal models. Existing approaches either synthesize missing modalities at high computational cost or apply prompt-based fine-tuning that relies only on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Hongye Zhu , Xuan Liu , Yanwen Ba , Jingye Xue , Shigeng Zhang

Large language model alignment via reinforcement learning depends critically on reward function quality. However, static, domain-specific reward models are often costly to train and exhibit poor generalization in out-of-distribution…

Computation and Language · Computer Science 2026-03-03 Andrew Zhuoer Feng , Cunxiang Wang , Bosi Wen , Yidong Wang , Yu Luo , Hongning Wang , Minlie Huang

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…

Artificial Intelligence · Computer Science 2025-12-01 Gunshi Gupta , Karmesh Yadav , Zsolt Kira , Yarin Gal , Rahaf Aljundi

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective solution is replay, which involves storing few previous…

Machine Learning · Computer Science 2023-08-04 Daniel Brignac , Niels Lobo , Abhijit Mahalanobis