English
Related papers

Related papers: Reward Prediction Error Prioritisation in Experien…

200 papers

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully…

Machine Learning · Computer Science 2019-02-19 Hao Liu , Alexander Trott , Richard Socher , Caiming Xiong

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

We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). ReF-ER was shown to outperform state of the art algorithms for continuous control in problems ranging…

Machine Learning · Computer Science 2022-09-05 Pascal Weber , Daniel Wälchli , Mustafa Zeqiri , Petros Koumoutsakos

Preference-based reinforcement learning (PbRL) has shown impressive capabilities in training agents without reward engineering. However, a notable limitation of PbRL is its dependency on substantial human feedback. This dependency stems…

Machine Learning · Computer Science 2024-05-30 Fengshuo Bai , Rui Zhao , Hongming Zhang , Sijia Cui , Ying Wen , Yaodong Yang , Bo Xu , Lei Han

In reinforcement learning, Reverse Experience Replay (RER) is a recently proposed algorithm that attains better sample complexity than the classic experience replay method. RER requires the learning algorithm to update the parameters…

Machine Learning · Computer Science 2024-09-02 Nan Jiang , Jinzhao Li , Yexiang Xue

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

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

This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these…

Machine Learning · Computer Science 2018-05-16 Tracy Wan , Neil Xu

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

Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy.…

Machine Learning · Computer Science 2025-01-09 Yang Yue , Bingyi Kang , Xiao Ma , Qisen Yang , Gao Huang , Shiji Song , Shuicheng Yan

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…

Machine Learning · Computer Science 2018-09-10 Sameera Lanka , Tianfu Wu

Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences. Recent algorithms such as Hindsight Experience Replay (HER)…

Robotics · Computer Science 2024-02-26 Erdi Sayar , Zhenshan Bing , Carlo D'Eramo , Ozgur S. Oguz , Alois Knoll

Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prioritization has to be balanced with sample diversity for…

Machine Learning · Computer Science 2020-11-30 Sanghwa Lee , Jaeyoung Lee , Ichiro Hasuo

Even though reinforcement-learning-based algorithms achieved superhuman performance in many domains, the field of robotics poses significant challenges as the state and action spaces are continuous, and the reward function is predominantly…

Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for behaviors from unlabeled videos, which are widely available on…

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

Back-stepping experience replay (BER) is a reinforcement learning technique that can accelerate learning efficiency in reversible environments. BER trains an agent with generated back-stepping transitions of collected experiences and normal…

Machine Learning · Computer Science 2024-12-23 Guwen Lyu , Masahiro Sato

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

Experience replay enables online reinforcement learning agents to store and reuse the previous experiences of interacting with the environment. In the original method, the experiences are sampled and replayed uniformly at random. A prior…

Machine Learning · Computer Science 2021-12-13 Fanchen Bu , Dong Eui Chang

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