English
Related papers

Related papers: Pseudorehearsal in value function approximation

200 papers

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…

Machine Learning · Computer Science 2020-05-01 Abhishek Gupta , Benjamin Eysenbach , Chelsea Finn , Sergey Levine

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which…

Machine Learning · Computer Science 2024-09-18 S. R. Eshwar , Mayank Motwani , Nibedita Roy , Gugan Thoppe

Zap Q-learning is a recent class of reinforcement learning algorithms, motivated primarily as a means to accelerate convergence. Stability theory has been absent outside of two restrictive classes: the tabular setting, and optimal stopping.…

Machine Learning · Computer Science 2020-07-17 Shuhang Chen , Adithya M. Devraj , Fan Lu , Ana Bušić , Sean P. Meyn

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a…

Machine Learning · Computer Science 2016-07-04 Heechul Jung , Jeongwoo Ju , Minju Jung , Junmo Kim

In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream. Hence many existing deep learning solutions suffer from a limited…

Machine Learning · Computer Science 2020-11-18 Alessia Bertugli , Stefano Vincenzi , Simone Calderara , Andrea Passerini

Discounted reinforcement learning is fundamentally incompatible with function approximation for control in continuing tasks. It is not an optimization problem in its usual formulation, so when using function approximation there is no…

Artificial Intelligence · Computer Science 2019-11-28 Abhishek Naik , Roshan Shariff , Niko Yasui , Hengshuai Yao , Richard S. Sutton

We investigate the effect of task ordering on continual learning performance. We conduct an extensive series of empirical experiments on synthetic and naturalistic datasets and show that reordering tasks significantly affects the amount of…

Machine Learning · Computer Science 2022-05-27 Samuel J. Bell , Neil D. Lawrence

Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [Watkins and Dayan,…

Machine Learning · Computer Science 2021-08-09 Matthew T. Regehr , Alex Ayoub

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting…

Artificial Intelligence · Computer Science 2018-10-23 Scott Fujimoto , Herke van Hoof , David Meger

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…

Machine Learning · Computer Science 2021-06-29 Hyuntak Cha , Jaeho Lee , Jinwoo Shin

Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from…

Machine Learning · Computer Science 2019-03-28 Luis Haug , Sebastian Tschiatschek , Adish Singla

Data rehearsal has emerged as a leading approach for mitigating catastrophic forgetting in Continual Reinforcement Learning (CRL). However, existing work remains confined to policy gradient frameworks, regularizing only actors due to the…

Machine Learning · Computer Science 2026-05-22 Benjamin Poole , Andrew Quinn , Li Yang , Minwoo Lee

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables agents to benefit…

Machine Learning · Computer Science 2023-03-29 Tongzhou Mu , Hao Su

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Riccardo Volpi , Diane Larlus , Grégory Rogez

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation,…

Catastrophic forgetting is a problem caused by neural networks' inability to learn data in sequence. After learning two tasks in sequence, performance on the first one drops significantly. This is a serious disadvantage that prevents many…

Machine Learning · Computer Science 2020-04-30 Wojciech Masarczyk , Ivona Tautkute

After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates achieved by intelligent animals. It thus may well be that we…

Machine Learning · Computer Science 2025-05-30 Daniel N. Nissani

This article presents a short and concise description of stochastic approximation algorithms in reinforcement learning of Markov decision processes. The algorithms can also be used as a suboptimal method for partially observed Markov…

Optimization and Control · Mathematics 2015-12-25 Vikram Krishnamurthy

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

Machine Learning · Computer Science 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

In complex environments with large discrete action spaces, effective decision-making is critical in reinforcement learning (RL). Despite the widespread use of value-based RL approaches like Q-learning, they come with a computational burden,…

Machine Learning · Computer Science 2024-05-17 Fares Fourati , Vaneet Aggarwal , Mohamed-Slim Alouini