English
Related papers

Related papers: Pseudorehearsal in value function approximation

200 papers

Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples. This practice means that sub-epochs comprise of independent random samples of the training data that…

Machine Learning · Computer Science 2019-06-20 Eliav Buchnik , Edith Cohen , Avinatan Hassidim , Yossi Matias

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Songze Li , Mingyu Gao , Tonghua Su , Xu-Yao Zhang , Zhongjie Wang

Quadratic approximations form a fundamental building block of machine learning methods. E.g., second-order optimizers try to find the Newton step into the minimum of a local quadratic proxy to the objective function; and the second-order…

Machine Learning · Computer Science 2025-01-29 Lukas Tatzel , Bálint Mucsányi , Osane Hackel , Philipp Hennig

In this paper we investigate two hypothesis regarding the use of deep reinforcement learning in multiple tasks. The first hypothesis is driven by the question of whether a deep reinforcement learning algorithm, trained on two similar tasks,…

Machine Learning · Computer Science 2019-09-24 João Ribeiro , Francisco S. Melo , João Dias

Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a…

Machine Learning · Computer Science 2020-11-05 Brendan O'Donoghue , Ian Osband , Catalin Ionescu

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems…

Machine Learning · Computer Science 2021-02-23 Guoqing Liu , Chuheng Zhang , Li Zhao , Tao Qin , Jinhua Zhu , Jian Li , Nenghai Yu , Tie-Yan Liu

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…

Machine Learning · Computer Science 2023-06-07 Nader Asadi , MohammadReza Davari , Sudhir Mudur , Rahaf Aljundi , Eugene Belilovsky

We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt…

Machine Learning · Computer Science 2019-06-18 Christos Kaplanis , Murray Shanahan , Claudia Clopath

Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classical two-stage paradigm: first learn…

Artificial Intelligence · Computer Science 2019-11-25 Tianyu Li , Bogdan Mazoure , Doina Precup , Guillaume Rabusseau

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential…

Computation and Language · Computer Science 2024-12-30 Megan Ung , Alicia Sun , Samuel J. Bell , Bhaktipriya Radharapu , Levent Sagun , Adina Williams

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address…

Machine Learning · Computer Science 2019-06-04 Mohammad Rostami , Soheil Kolouri , Praveen K. Pilly

Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new tasks erases knowledge…

Machine Learning · Statistics 2021-07-12 Sebastian Lee , Sebastian Goldt , Andrew Saxe

In reinforcement learning (RL), Q-learning is a fundamental algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To overcome this…

Machine Learning · Computer Science 2026-02-04 Hyukjun Yang , Han-Dong Lim , Donghwan Lee

Q-learning is a widely used algorithm in reinforcement learning (RL), but its convergence can be slow, especially when the discount factor is close to one. Successive Over-Relaxation (SOR) Q-learning, which introduces a relaxation factor to…

Machine Learning · Computer Science 2025-07-01 Shreyas S R

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of…

Machine Learning · Computer Science 2019-02-25 Aswin Raghavan , Jesse Hostetler , Sek Chai

Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In…

Machine Learning · Computer Science 2023-02-14 Sen Lin , Peizhong Ju , Yingbin Liang , Ness Shroff

Planning and reinforcement learning are two key approaches to sequential decision making. Multi-step approximate real-time dynamic programming, a recently successful algorithm class of which AlphaZero [Silver et al., 2018] is an example,…

Artificial Intelligence · Computer Science 2020-05-18 Thomas M. Moerland , Anna Deichler , Simone Baldi , Joost Broekens , Catholijn M. Jonker

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…

Computation and Language · Computer Science 2019-06-03 Alexandra Chronopoulou , Christos Baziotis , Alexandros Potamianos