English
Related papers

Related papers: Improving Experience Replay with Successor Represe…

200 papers

Reinforcement Learning (RL) has achieved impressive success in post-training Large Language Models (LLMs) and Vision-Language Models (VLMs), with on-policy algorithms such as PPO, GRPO, and REINFORCE++ serving as the dominant paradigm.…

Computation and Language · Computer Science 2026-04-21 Weiyu Ma , Yongcheng Zeng , Yan Song , Xinyu Cui , Jian Zhao , Xuhui Liu , Mohamed Elhoseiny

Experience reuse is key to sample-efficient reinforcement learning. One of the critical issues is how the experience is represented and stored. Previously, the experience can be stored in the forms of features, individual models, and the…

Machine Learning · Computer Science 2019-06-03 Wen-Ji Zhou , Yang Yu , Yingfeng Chen , Kai Guan , Tangjie Lv , Changjie Fan , Zhi-Hua Zhou

This paper introduces an approach to Reinforcement Learning Algorithm by comparing their immediate rewards using a variation of Q-Learning algorithm. Unlike the conventional Q-Learning, the proposed algorithm compares current reward with…

Machine Learning · Computer Science 2010-09-15 Punit Pandey , Deepshikha Pandey , Shishir Kumar

We introduce a problem-level prioritization framework for RL post-training of large language models. Building on insights from prioritized replay in deep RL, as well as prior observations that rollouts with intermediate success rates tend…

Machine Learning · Computer Science 2026-01-07 Mehdi Fatemi

A commonly used heuristic in RL is experience replay (e.g.~\citet{lin1993reinforcement, mnih2015human}), in which a learner stores and re-uses past trajectories as if they were sampled online. In this work, we initiate a rigorous study of…

Machine Learning · Computer Science 2021-12-09 Liran Szlak , Ohad Shamir

Prioritized Experience Replay (PER) enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that…

Machine Learning · Computer Science 2023-11-27 Zhuoying Chen , Huiping Li , Zhaoxu Wang

This paper introduces the QDQN-DPER framework to enhance the efficiency of quantum reinforcement learning (QRL) in solving sequential decision tasks. The framework incorporates prioritized experience replay and asynchronous training into…

Quantum Physics · Physics 2023-04-20 Samuel Yen-Chi Chen

Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…

Machine Learning · Computer Science 2026-02-04 Hua Zheng , Wei Xie , M. Ben Feng

For reinforcement learning on complex stochastic systems where many factors dynamically impact the output trajectories, it is desirable to effectively leverage the information from historical samples collected in previous iterations to…

Machine Learning · Statistics 2022-09-13 Hua Zheng , Wei Xie , M. Ben Feng

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Machine Learning · Computer Science 2019-12-30 Qisheng Wang , Qichao Wang

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Machine Learning · Computer Science 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

Artificial neural networks (ANNs) continue to face challenges in continual learning, particularly due to catastrophic forgetting, the loss of previously learned knowledge when acquiring new tasks. Inspired by memory consolidation in the…

Machine Learning · Computer Science 2025-09-03 Jina Kim

Off-policy sampling and experience replay are key for improving sample efficiency and scaling model-free temporal difference learning methods. When combined with function approximation, such as neural networks, this combination is known as…

Machine Learning · Computer Science 2021-07-13 Ray Jiang , Shangtong Zhang , Veronica Chelu , Adam White , Hado van Hasselt

Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm for sparse reward functions. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in the episode. Virtual…

Machine Learning · Computer Science 2021-03-09 Binyamin Manela , Armin Biess

Memory replay may be key to learning in biological brains, which manage to learn new tasks continually without catastrophically interfering with previous knowledge. On the other hand, artificial neural networks suffer from catastrophic…

Machine Learning · Computer Science 2022-01-06 Haitz Sáez de Ocáriz Borde

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

Currently, deep reinforcement learning (RL) shows impressive results in complex gaming and robotic environments. Often these results are achieved at the expense of huge computational costs and require an incredible number of episodes of…

Machine Learning · Computer Science 2020-06-18 Alexey Skrynnik , Aleksey Staroverov , Ermek Aitygulov , Kirill Aksenov , Vasilii Davydov , Aleksandr I. Panov

Recent work in deep reinforcement learning has allowed algorithms to learn complex tasks such as Atari 2600 games just from the reward provided by the game, but these algorithms presently require millions of training steps in order to…

Machine Learning · Computer Science 2018-01-09 Benjamin Spector , Serge Belongie

Advances in reinforcement learning (RL) often rely on massive compute resources and remain notoriously sample inefficient. In contrast, the human brain is able to efficiently learn effective control strategies using limited resources. This…

Machine Learning · Computer Science 2024-01-30 Burcu Küçükoğlu , Walraaf Borkent , Bodo Rueckauer , Nasir Ahmad , Umut Güçlü , Marcel van Gerven

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal oracle evaluations (computational prediction or wet-lab experiment).…

Biomolecules · Quantitative Biology 2023-05-26 Jeff Guo , Philippe Schwaller
‹ Prev 1 3 4 5 6 7 10 Next ›