English
Related papers

Related papers: Efficient RL Training for LLMs with Experience Rep…

200 papers

Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL). We present an effective yet simple framework to extend the use of replays across multiple experiments, minimally…

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Truman Hickok , Dhireesha Kudithipudi

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

In reinforcement learning, experience replay stores past samples for further reuse. Prioritized sampling is a promising technique to better utilize these samples. Previous criteria of prioritization include TD error, recentness and…

Machine Learning · Computer Science 2021-11-10 Xu-Hui Liu , Zhenghai Xue , Jing-Cheng Pang , Shengyi Jiang , Feng Xu , Yang Yu

Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand. Contemporary off-policy algorithms either replay past experiences uniformly or utilize…

Machine Learning · Computer Science 2019-06-21 Daochen Zha , Kwei-Herng Lai , Kaixiong Zhou , Xia Hu

The utilization of the experience replay mechanism enables agents to effectively leverage their experiences on several occasions. In previous studies, the sampling probability of the transitions was modified based on their relative…

Machine Learning · Computer Science 2024-06-14 Arda Sarp Yenicesu , Furkan B. Mutlu , Suleyman S. Kozat , Ozgur S. Oguz

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

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the…

Machine Learning · Computer Science 2025-01-31 Hoda Yamani , Yuning Xing , Lee Violet C. Ong , Bruce A. MacDonald , Henry Williams

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic and extensive analysis of experience replay in Q-learning…

Machine Learning · Computer Science 2020-07-15 William Fedus , Prajit Ramachandran , Rishabh Agarwal , Yoshua Bengio , Hugo Larochelle , Mark Rowland , Will Dabney

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, and existing work…

Machine Learning · Computer Science 2026-02-17 Yifan Sun , Jingyan Shen , Yibin Wang , Tianyu Chen , Zhendong Wang , Mingyuan Zhou , Huan Zhang

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

Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the literature to tackle the Continual Learning challenge. Among…

Machine Learning · Computer Science 2022-11-30 Gabriele Merlin , Vincenzo Lomonaco , Andrea Cossu , Antonio Carta , Davide Bacciu

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

Machine Learning · Computer Science 2025-07-08 Shihan Dou , Muling Wu , Jingwen Xu , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and resource-conserving approach would be continual…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Machine Learning · Computer Science 2019-10-31 Rahaf Aljundi , Lucas Caccia , Eugene Belilovsky , Massimo Caccia , Min Lin , Laurent Charlin , Tinne Tuytelaars

While off-policy reinforcement learning (RL) algorithms are sample efficient due to gradient-based updates and data reuse in the replay buffer, they struggle with convergence to local optima due to limited exploration. On the other hand,…

Machine Learning · Computer Science 2023-05-05 Bowen Zheng , Ran Cheng

Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data collected in previous iterations to accelerate policy optimization. Classical experience replay treats all past observations uniformly…

Machine Learning · Statistics 2026-02-06 Hua Zheng , Wei Xie , M. Ben Feng , Keilung Choy

Experience replay, which enables the agents to remember and reuse experience from the past, has played a significant role in the success of off-policy reinforcement learning (RL). To utilize the experience replay efficiently, the existing…

Machine Learning · Computer Science 2021-04-08 Youngmin Oh , Kimin Lee , Jinwoo Shin , Eunho Yang , Sung Ju Hwang

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

Artificial Intelligence · Computer Science 2022-09-29 Thommen George Karimpanal , Roland Bouffanais