English
Related papers

Related papers: Reconciling $\lambda$-Returns with Experience Repl…

200 papers

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

Q-learning played a foundational role in the field reinforcement learning (RL). However, TD algorithms with off-policy data, such as Q-learning, or nonlinear function approximation like deep neural networks require several additional tricks…

Machine Learning · Computer Science 2025-04-23 Matteo Gallici , Mattie Fellows , Benjamin Ellis , Bartomeu Pou , Ivan Masmitja , Jakob Nicolaus Foerster , Mario Martin

Multi-step methods such as Retrace($\lambda$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations…

Machine Learning · Computer Science 2019-02-11 J. Fernando Hernandez-Garcia , Richard S. Sutton

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

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of…

Artificial Intelligence · Computer Science 2016-08-12 Anna Harutyunyan , Marc G. Bellemare , Tom Stepleton , Remi Munos

Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…

Machine Learning · Computer Science 2019-05-30 Zhouyuan Huo , Bin Gu , Heng 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…

We study the multi-step off-policy learning approach to distributional RL. Despite the apparent similarity between value-based RL and distributional RL, our study reveals intriguing and fundamental differences between the two cases in the…

Machine Learning · Computer Science 2022-07-18 Yunhao Tang , Mark Rowland , Rémi Munos , Bernardo Ávila Pires , Will Dabney , Marc G. Bellemare

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

Building upon the recent success of deep reinforcement learning methods, we investigate the possibility of on-policy reinforcement learning improvement by reusing the data from several consecutive policies. On-policy methods bring many…

Machine Learning · Computer Science 2019-01-21 Dmitry Kangin , Nicolas Pugeault

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value…

Machine Learning · Computer Science 2018-10-19 Steven Hansen , Pablo Sprechmann , Alexander Pritzel , André Barreto , Charles Blundell

Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning. One challenging problem when applying DQN or other…

Machine Learning · Computer Science 2022-09-19 Zhe Zhang , Yukun Zou , Junjie Lai , Qing Xu

Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective solution is replay, which involves storing few previous…

Machine Learning · Computer Science 2023-08-04 Daniel Brignac , Niels Lobo , Abhijit Mahalanobis

While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that…

Machine Learning · Computer Science 2023-11-14 Felix den Breejen , Sangmin Bae , Stephen Cha , Tae-Young Kim , Seoung Hyun Koh , Se-Young Yun

A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…

Machine Learning · Computer Science 2019-04-18 Gido M. van de Ven , Andreas S. Tolias

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features of the observations…

Machine Learning · Computer Science 2018-10-31 Yuri Burda , Harrison Edwards , Amos Storkey , Oleg Klimov

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-10-27 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Prioritized Experience Replay (PER) is a technical means of deep reinforcement learning by selecting experience samples with more knowledge quantity to improve the training rate of neural network. However, the non-uniform sampling used in…

Machine Learning · Computer Science 2023-10-10 Zhuoying Chen , Huiping Li , Rizhong Wang

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Machine Learning · Computer Science 2023-08-04 Quanziang Wang , Renzhen Wang , Yuexiang Li , Dong Wei , Kai Ma , Yefeng Zheng , Deyu Meng