paper-with-me

Papers

MGSER-SAM: Memory-Guided Soft Experience Replay with Sharpness-Aware Optimization for Enhanced Continual Learning

2024-05-15 · Xingyu Li, Bo Tang

Deep neural networks suffer from the catastrophic forgetting problem in the field of continual learning (CL). To address this challenge, we propose MGSER-SAM, a novel memory replay-based algorithm specifically engineered to enhance the generalization capabilities of CL models. We first intergrate the SAM optimizer, a component designed for optimizing flatness, which seamlessly fits into well-known Experience Replay frameworks such as ER and DER++. Then, MGSER-SAM distinctively addresses the complex challenge of reconciling conflicts in weight perturbation directions between ongoing tasks and previously stored memories, which is underexplored in the SAM optimizer. This is effectively accomplished by the strategic integration of soft logits and the alignment of memory gradient directions, where the regularization terms facilitate the concurrent minimization of various training loss terms integral to the CL process. Through rigorous experimental analysis conducted across multiple benchmarks, MGSER-SAM has demonstrated a consistent ability to outperform existing baselines in all three CL scenarios. Comparing to the representative memory replay-based baselines ER and DER++, MGSER-SAM not only improves the testing accuracy by $24.4\%$ and $17.6\%$ respectively, but also achieves the lowest forgetting on each benchmark.

📄 PDF Abstract BibTeX arXiv:2405.09492

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

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},…
SAM 설명 없음

Similar Papers 제목 키워드 기반

Saliency Guided Experience Packing for Replay in Continual Learning

2021-09-10 · Gobinda Saha, Kaushik Roy

Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to store past experiences in the form of…

Continual LearningImage Classification

Associative Memory Based Experience Replay for Deep Reinforcement Learning

2022-07-16 · Mengyuan Li, Arman Kazemi, Ann Franchesca Laguna, X. Sharon Hu

Experience replay is an essential component in deep reinforcement learning (DRL), which stores the experiences and generates experiences for the agent to learn in real time. Recently, prioritized experience replay (PER) …

CPUDeep Reinforcement LearningGPUreinforcement-learning+2

Reverse Experience Replay

2019-10-19 · Egor Rotinov

This paper describes an improvement in Deep Q-learning called Reverse Experience Replay (also RER) that solves the problem of sparse rewards and helps to deal with reward maximizing tasks by sampling transitions successi…

Q-Learning

Deep In-GPU Experience Replay

2018-01-09 · Ben Parr

Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and…

CPUGPUReinforcement Learning

Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay

2023-05-01 · ICLR 2023 5 · Hongming Zhang, Chenjun Xiao, Han Wang, Jun Jin 외

Experience replay, which stores transitions in a replay memory for repeated use, plays an important role of improving sample efficiency in reinforcement learning. Existing techniques such as reweighted sampling, episodic…