English
Related papers

Related papers: Improving Experience Replay with Successor Represe…

200 papers

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

In continual learning, model needs to continually learn a feature extractor and classifier on a sequence of tasks. This paper focuses on how to learn a classifier based on a pretrained feature extractor under continual learning setting. We…

Machine Learning · Computer Science 2023-02-24 Ziheng Li , Shibo Jie , Zhi-Hong Deng

XCS constitutes the most deeply investigated classifier system today. It bears strong potentials and comes with inherent capabilities for mastering a variety of different learning tasks. Besides outstanding successes in various…

Machine Learning · Computer Science 2020-02-14 Anthony Stein , Roland Maier , Lukas Rosenbauer , Jörg Hähner

Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt…

Machine Learning · Computer Science 2026-03-24 Andrei Baroian , Rutger Berger

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience. These outcome-conditioned imitation learning methods are…

Machine Learning · Computer Science 2023-02-21 Benjamin Eysenbach , Soumith Udatha , Sergey Levine , Ruslan Salakhutdinov

A remarkable capacity of the brain is its ability to autonomously reorganize memories during offline periods. Memory replay, a mechanism hypothesized to underlie biological offline learning, has inspired offline methods for reducing…

Neural and Evolutionary Computing · Computer Science 2023-01-18 Zhenglong Zhou , Geshi Yeung , Anna C. Schapiro

Any reinforcement learning system must be able to identify which past events contributed to observed outcomes, a problem known as credit assignment. A common solution to this problem is to use an eligibility trace to assign credit to…

Machine Learning · Computer Science 2022-07-26 Duncan Bailey , Marcelo G. Mattar

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

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an…

Machine Learning · Computer Science 2021-12-14 Pierre Liotet , Francesco Vidaich , Alberto Maria Metelli , Marcello Restelli

The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow for better-than-demonstrator performance, preferences over…

Machine Learning · Computer Science 2019-10-15 Daniel S. Brown , Wonjoon Goo , Scott Niekum

Humans possess the ability to draw on past experiences explicitly when learning new tasks and applying them accordingly. We believe this capacity for self-referencing is especially advantageous for reinforcement learning agents in the…

Machine Learning · Computer Science 2023-11-17 Andrew Zhao , Erle Zhu , Rui Lu , Matthieu Lin , Yong-Jin Liu , Gao Huang

Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the…

Robotics · Computer Science 2020-11-12 Pierre Aumjaud , David McAuliffe , Francisco Javier Rodríguez Lera , Philip Cardiff

Memorization impacts the performance of deep learning algorithms. Prior works have studied memorization primarily in the context of generalization and privacy. This work studies the memorization effect on incremental learning scenarios.…

Machine Learning · Computer Science 2025-05-26 Jędrzej Kozal , Jan Wasilewski , Alif Ashrafee , Bartosz Krawczyk , Michał Woźniak

In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on…

Machine Learning · Computer Science 2024-07-22 Jason Yoo , Yunpeng Liu , Frank Wood , Geoff Pleiss

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

This paper proposes a method for prioritizing the replay experience referred to as Hindsight Goal Ranking (HGR) in overcoming the limitation of Hindsight Experience Replay (HER) that generates hindsight goals based on uniform sampling. HGR…

Machine Learning · Computer Science 2021-10-29 Tung M. Luu , Chang D. Yoo

Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…

Machine Learning · Computer Science 2025-05-20 Truman Hickok

Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled…

Artificial Intelligence · Computer Science 2018-01-11 Ben Parr

Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks…

Machine Learning · Computer Science 2019-11-28 Craig Atkinson , Brendan McCane , Lech Szymanski , Anthony Robins

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Machine Learning · Computer Science 2024-07-17 Luke Yang , Levin Kuhlmann , Gideon Kowadlo