paper-with-me

Papers

Data-Incremental Continual Offline Reinforcement Learning

2024-04-19 · Sibo Gai, Donglin Wang

In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of datasets of a single offline reinforcement learning (RL) task continually, instead of learning a sequence of offline RL tasks with respective datasets. Then, we propose that this new setting will introduce a unique challenge to continual learning: active forgetting, which means that the agent will forget the learnt skill actively. The main reason for active forgetting is conservative learning used by offline RL, which is used to solve the overestimation problem. With conservative learning, the offline RL method will suppress the value of all actions, learnt or not, without selection, unless it is in the just learning dataset. Therefore, inferior data may overlay premium data because of the learning sequence. To solve this problem, we propose a new algorithm, called experience-replay-based ensemble implicit Q-learning (EREIQL), which introduces multiple value networks to reduce the initial value and avoid using conservative learning, and the experience replay to relieve catastrophic forgetting. Our experiments show that EREIQL relieves active forgetting in DICORL and performs well.

📄 PDF Abstract BibTeX arXiv:2404.12639

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningOffline RLQ-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
Focus 설명 없음
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

CoMPS: Continual Meta Policy Search

2021-12-08 · ICLR 2022 4 · Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn 외

We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforc…

Continual Learningcontinuous-controlContinuous ControlMeta-Learning+5

Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning

2017-06-19 · Nick Erickson, Qi Zhao

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel …

Continual LearningDeep Reinforcement LearningGeneral Reinforcement LearningIncremental Learning+3

Self-Supervised Training Enhances Online Continual Learning

2021-03-25 · Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale i…

Continual Learningimage-classificationImage Classification

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data

2023-04-08 · Elena Camuffo, Simone Milani

During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge disti…

class-incremental learningClass Incremental LearningContinual Learningimage-classification+6

Recent Advances of Foundation Language Models-based Continual Learning: A Survey

2024-05-28 · Yutao Yang, Jie zhou, Xuanwen Ding, Tianyu Huai 외

Recently, foundation language models (LMs) have marked significant achievements in the domains of natural language processing (NLP) and computer vision (CV). Unlike traditional neural network models, foundation LMs obtai…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1