English
Related papers

Related papers: Off-Policy Correction for Deep Deterministic Polic…

200 papers

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions…

Machine Learning · Computer Science 2016-02-26 Tom Schaul , John Quan , Ioannis Antonoglou , David Silver

In goal-conditioned offline reinforcement learning, an agent learns from previously collected data to go to an arbitrary goal. Since the offline data only contains a finite number of trajectories, a main challenge is how to generate more…

Machine Learning · Computer Science 2023-03-07 Wenyan Yang , Joni Pajarinen , Dinging Cai , Joni Kämäräinen

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…

Machine Learning · Computer Science 2026-03-03 Daniel Ritter , Owen Oertell , Bradley Guo , Jonathan Chang , Kianté Brantley , Wen Sun

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

Hindsight experience replay (HER) is a goal relabelling technique typically used with off-policy deep reinforcement learning algorithms to solve goal-oriented tasks; it is well suited to robotic manipulation tasks that deliver only sparse…

Machine Learning · Computer Science 2021-11-10 Tianhong Dai , Hengyan Liu , Kai Arulkumaran , Guangyu Ren , Anil Anthony Bharath

Experience replay (ER) improves the data efficiency of off-policy reinforcement learning (RL) algorithms by allowing an agent to store and reuse its past experiences in a replay buffer. While many techniques have been proposed to enhance ER…

Machine Learning · Computer Science 2021-04-06 Yunshu Du , Garrett Warnell , Assefaw Gebremedhin , Peter Stone , Matthew E. Taylor

Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data…

Machine Learning · Computer Science 2022-06-16 Raghuram Bharadwaj Diddigi , Prateek Jain , Prabuchandran K. J. , Shalabh Bhatnagar

Experience replay (ER) used in (deep) reinforcement learning is considered to be applicable only to off-policy algorithms. However, there have been some cases in which ER has been applied for on-policy algorithms, suggesting that…

Machine Learning · Computer Science 2024-09-16 Taisuke Kobayashi

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

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

Policy-based Reinforcement Learning (RL) has established itself as the dominant paradigm in generative recommendation for optimizing sequential user interactions. However, when applied to offline historical logs, these methods suffer a…

Machine Learning · Computer Science 2026-02-12 Jie Jiang , Yusen Huo , Xiangxin Zhan , Changping Wang , Jun Zhang

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature…

Machine Learning · Computer Science 2025-01-28 Qing Wang , Yingru Li , Jiechao Xiong , Tong Zhang

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

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

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based…

Machine Learning · Computer Science 2025-01-14 Yuyang Chen , Kaiyan Zhao , Yiming Wang , Ming Yang , Jian Zhang , Xiaoguang Niu