English
Related papers

Related papers: Remember and Forget for Experience Replay

200 papers

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate…

Machine Learning · Computer Science 2020-10-13 Pietro Buzzega , Matteo Boschini , Angelo Porrello , Simone Calderara

Recently experience replay is widely used in various deep reinforcement learning (RL) algorithms, in this paper we rethink the utility of experience replay. It introduces a new hyper-parameter, the memory buffer size, which needs carefully…

Machine Learning · Computer Science 2018-05-01 Shangtong Zhang , Richard S. Sutton

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

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

Deep Reinforcement Learning (RL) methods rely on experience replay to approximate the minibatched supervised learning setting; however, unlike supervised learning where access to lots of training data is crucial to generalization,…

Machine Learning · Computer Science 2021-02-24 Brett Daley , Cameron Hickert , Christopher Amato

Hindsight experience replay (HER) is well-known to accelerate goal-based reinforcement learning (RL). While HER is generally applied to off-policy RL algorithms, we previously showed that HER can also accelerate on-policy algorithms, such…

Machine Learning · Computer Science 2024-11-01 Douglas C. Crowder , Matthew L. Trappett , Darrien M. McKenzie , Frances S. Chance

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

Machine Learning · Computer Science 2023-04-12 Qingfeng Lan , Yangchen Pan , Jun Luo , A. Rupam Mahmood

While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that…

Machine Learning · Computer Science 2026-04-13 Charles Arnal , Vivien Cabannes , Taco Cohen , Julia Kempe , Remi Munos

Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error…

Machine Learning · Computer Science 2021-02-08 Ang A. Li , Zongqing Lu , Chenglin Miao

The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under…

Machine Learning · Computer Science 2024-04-23 Sibo Gai , Donglin Wang , Li He

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…

Machine Learning · Computer Science 2021-02-04 Mirza Ramicic , Andrea Bonarini

Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization,…

Machine Learning · Computer Science 2025-09-19 Tianyang Duan , Zongyuan Zhang , Songxiao Guo , Yuanye Zhao , Zheng Lin , Zihan Fang , Yi Liu , Dianxin Luan , Dong Huang , Heming Cui , Yong Cui

Efficient utilization of the replay buffer plays a significant role in the off-policy actor-critic reinforcement learning (RL) algorithms used for model-free control policy synthesis for complex dynamical systems. We propose a method for…

Machine Learning · Computer Science 2024-02-13 Nikhil Kumar Singh , Indranil Saha

Reinforcement learning (RL) for large language models is an energy-intensive endeavor: training can be unstable, and the policy may gradually drift away from its pretrained weights. We present \emph{RLEP}\, -- \,Reinforcement Learning with…

Computation and Language · Computer Science 2025-07-11 Hongzhi Zhang , Jia Fu , Jingyuan Zhang , Kai Fu , Qi Wang , Fuzheng Zhang , Guorui Zhou

Recent advances in off-policy deep reinforcement learning (RL) have led to impressive success in complex tasks from visual observations. Experience replay improves sample-efficiency by reusing experiences from the past, and convolutional…

Machine Learning · Computer Science 2021-10-29 Lili Chen , Kimin Lee , Aravind Srinivas , Pieter Abbeel

Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…

Machine Learning · Computer Science 2025-12-05 Yasuhiro Fujita

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

The experience replay mechanism allows agents to use the experiences multiple times. In prior works, the sampling probability of the transitions was adjusted according to their importance. Reassigning sampling probabilities for every…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Furkan B. Mutlu , Suleyman S. Kozat

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific…

Machine Learning · Computer Science 2025-12-16 Leonard S. Pleiss , Tobias Sutter , Maximilian Schiffer

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 successively in reverse…

Machine Learning · Computer Science 2019-10-24 Egor Rotinov