paper-with-me

홈 › Papers

Knowledge Retention for Continual Model-Based Reinforcement Learning

2025-03-06 · Yixiang Sun, Haotian Fu, Michael Littman, George Konidaris

We propose DRAGO, a novel approach for continual model-based reinforcement learning aimed at improving the incremental development of world models across a sequence of tasks that differ in their reward functions but not the state space or dynamics. DRAGO comprises two key components: Synthetic Experience Rehearsal, which leverages generative models to create synthetic experiences from past tasks, allowing the agent to reinforce previously learned dynamics without storing data, and Regaining Memories Through Exploration, which introduces an intrinsic reward mechanism to guide the agent toward revisiting relevant states from prior tasks. Together, these components enable the agent to maintain a comprehensive and continually developing world model, facilitating more effective learning and adaptation across diverse environments. Empirical evaluations demonstrate that DRAGO is able to preserve knowledge across tasks, achieving superior performance in various continual learning scenarios.

📄 PDF Abstract BibTeX arXiv:2503.04256

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Continual Knowledge Adaptation for Reinforcement Learning

2025-10-22 · Jinwu Hu, Zihao Lian, Zhiquan Wen, Chenghao Li 외 arxiv

Reinforcement Learning enables agents to learn optimal behaviors through interactions with environments. However, real-world environments are typically non-stationary, requiring agents to continuously adapt to new tasks …

Reinforcement Learning

Balanced Gradient Sample Retrieval for Enhanced Knowledge Retention in Proxy-based Continual Learning

2024-12-19 · Hongye Xu, Jan Wasilewski, Bartosz Krawczyk

Continual learning in deep neural networks often suffers from catastrophic forgetting, where representations for previous tasks are overwritten during subsequent training. We propose a novel sample retrieval strategy fro…

Continual LearningContrastive LearningDiversityRetrieval

To Retain or to Adapt? Generalizing Continual Learning

2026-07-06 · Giulia Lanzillotta, Mandana Samiei, Doina Precup, Razvan Pascanu 외 arxiv

The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, often unstated assumption: that a lifelong learner should approximate th…

Reinforcement LearningImage ClassificationContinual Learning

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models

2024-11-09 · Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao 외

Continual learning (CL) is crucial for language models to dynamically adapt to the evolving real-world demands. To mitigate the catastrophic forgetting problem in CL, data replay has been proven a simple and effective st…

Continual Learning

Online Continual Knowledge Learning for Language Models

2023-11-16 · Yuhao Wu, Tongjun Shi, Karthick Sharma, Chun Wei Seah 외

Large Language Models (LLMs) serve as repositories of extensive world knowledge, enabling them to perform tasks such as question-answering and fact-checking. However, this knowledge can become obsolete as global contexts…

Continual LearningFact CheckingQuestion AnsweringWorld Knowledge