尽管对历史数据的访问权限有限，但在不断学习的情况下，重播方法已成功地减轻灾难性遗忘而成功。但是，在许多现实世界中，存储历史数据都很便宜，但是由于处理时间限制，将禁止重播所有历史数据。在这种情况下，我们建议学习学习的时间来学习连续学习系统，在该系统中，我们将学习重播时间表，以在不同的时间步骤中重播哪些任务。为了证明学习时间的重要性，我们首先使用蒙特卡洛树搜索来找到适当的重播时间表，并表明它可以根据持续的学习表现优于固定的调度策略。此外，为了提高调度效率本身，我们建议使用强化学习来学习重播调度策略，这些策略可以推广到新的持续学习场景而不增加计算成本。在我们的实验中，我们展示了学习学习时间的优势，这使当前的持续学习研究更接近现实世界的需求。

持续学习的目标（CL）是随着时间的推移学习不同的任务。与CL相关的主要Desiderata是在旧任务上保持绩效，利用后者来改善未来任务的学习，并在培训过程中引入最小的开销（例如，不需要增长的模型或再培训）。我们建议通过固定密度的稀疏神经网络来解决这些避难所的神经启发性塑性适应（NISPA）体系结构。 NISPA形成了稳定的途径，可以从较旧的任务中保存知识。此外，NISPA使用连接重新设计来创建新的塑料路径，以重用有关新任务的现有知识。我们对EMNIST，FashionMnist，CIFAR10和CIFAR100数据集的广泛评估表明，NISPA的表现明显胜过代表性的最先进的持续学习基线，并且与盆地相比，它的可学习参数最多少了十倍。我们还认为稀疏是持续学习的重要组成部分。 NISPA代码可在https://github.com/burakgurbuz97/nispa上获得。

持续学习（CL）旨在开发单一模型适应越来越多的任务的技术，从而潜在地利用跨任务的学习以资源有效的方式。 CL系统的主要挑战是灾难性的遗忘，在学习新任务时忘记了早期的任务。为了解决此问题，基于重播的CL方法在遇到遇到任务中选择的小缓冲区中维护和重复培训。我们提出梯度Coreset重放（GCR），一种新颖的重播缓冲区选择和使用仔细设计的优化标准的更新策略。具体而言，我们选择并维护一个“Coreset”，其与迄今为止关于当前模型参数的所有数据的梯度紧密近似，并讨论其有效应用于持续学习设置所需的关键策略。在学习的离线持续学习环境中，我们在最先进的最先进的最先进的持续学习环境中表现出显着的收益（2％-4％）。我们的调查结果还有效地转移到在线/流媒体CL设置，从而显示现有方法的5％。最后，我们展示了持续学习的监督对比损失的价值，当与我们的子集选择策略相结合时，累计增益高达5％。

持续的学习方法努力减轻灾难性遗忘（CF），在学习新任务时，从以前学习的任务中丢失了知识。在这些算法中，有些在训练时维护以前任务中的样本子集。这些样本称为内存。这些方法表现出出色的性能，同时在概念上简单易于实现。然而，尽管它们很受欢迎，但几乎没有做任何事情来理解要包含在记忆中的元素。当前，这种记忆通常是通过随机抽样填充的，没有指导原则可以有助于保留以前的知识。在这项工作中，我们提出了一个基于称为一致性意识采样（CAWS）的样本的学习一致性的标准。该标准优先考虑通过深网更容易学习的样本。我们对三种不同的基于内存的方法进行研究：AGEM，GDUMB和经验重播，在MNIST，CIFAR-10和CIFAR-100数据集上。我们表明，使用最一致的元素在受到计算预算的约束时会产生性能提高；如果在没有这种约束的情况下，随机抽样是一个强大的基线。但是，在经验重播上使用CAWS可以改善随机基线的性能。最后，我们表明CAWS取得了与流行的内存选择方法相似的结果，同时需要大大减少计算资源。

We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting in substantial boosts in their performance. We further show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. These observations point towards EBMs as a useful building block for future continual learning methods.

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. 1 We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods and 4 baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.

模块化是持续学习（CL）的令人信服的解决方案，是相关任务建模的问题。学习和组合模块来解决不同的任务提供了一种抽象来解决CL的主要挑战，包括灾难性的遗忘，向后和向前传输跨任务以及子线性模型的增长。我们引入本地模块组成（LMC），该方法是模块化CL的方法，其中每个模块都提供了局部结构组件，其估计模块与输入的相关性。基于本地相关评分进行动态模块组合。我们展示了对任务身份（IDS）的不可知性来自（本地）结构学习，该结构学习是特定于模块和/或模型特定于以前的作品，使LMC适用于与以前的作品相比的更多CL设置。此外，LMC还跟踪输入分布的统计信息，并在检测到异常样本时添加新模块。在第一组实验中，LMC与最近的持续转移学习基准上的现有方法相比，不需要任务标识。在另一个研究中，我们表明结构学习的局部性允许LMC插入相关但未遵守的任务（OOD），以及在不同任务序列上独立于不同的任务序列培训的模块化网络，而无需任何微调。最后，在寻找LMC的限制，我们在30和100个任务的更具挑战性序列上研究它，展示了本地模块选择在存在大量候选模块时变得更具挑战性。在此设置中，与Oracle基准的基线相比，最佳执行LMC产生的模块更少，但它达到了较低的总体精度。 CodeBase可在https://github.com/oleksost/lmc下找到。

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference among tasks, and the inability to exploit previous knowledge. While considerable research has focused on learning multiple input distributions, typically in classification, lifelong reinforcement learning (LRL) must also deal with variations in the state and transition distributions, and in the reward functions. Modulating masks, recently developed for classification, are particularly suitable to deal with such a large spectrum of task variations. In this paper, we adapted modulating masks to work with deep LRL, specifically PPO and IMPALA agents. The comparison with LRL baselines in both discrete and continuous RL tasks shows competitive performance. We further investigated the use of a linear combination of previously learned masks to exploit previous knowledge when learning new tasks: not only is learning faster, the algorithm solves tasks that we could not otherwise solve from scratch due to extremely sparse rewards. The results suggest that RL with modulating masks is a promising approach to lifelong learning, to the composition of knowledge to learn increasingly complex tasks, and to knowledge reuse for efficient and faster learning.

深度神经网络的强大学习能力使强化学习者能够直接从连续环境中学习有效的控制政策。从理论上讲，为了实现稳定的性能，神经网络假设I.I.D.不幸的是，在训练数据在时间上相关且非平稳的一般强化学习范式中，输入不存在。这个问题可能导致“灾难性干扰”和性能崩溃的现象。在本文中，我们提出智商，即干涉意识深度Q学习，以减轻单任务深度加固学习中的灾难性干扰。具体来说，我们求助于在线聚类，以实现在线上下文部门，以及一个多头网络和一个知识蒸馏正规化术语，用于保留学习上下文的政策。与现有方法相比，智商基于深Q网络，始终如一地提高稳定性和性能，并通过对经典控制和ATARI任务进行了广泛的实验。该代码可在以下网址公开获取：https：//github.com/sweety-dm/interference-aware-ware-deep-q-learning。

我们开发了一种新的持续元学习方法，以解决连续多任务学习中的挑战。在此设置中，代理商的目标是快速通过任何任务序列实现高奖励。先前的Meta-Creenifiltive学习算法已经表现出有希望加速收购新任务的结果。但是，他们需要在培训期间访问所有任务。除了简单地将过去的经验转移到新任务，我们的目标是设计学习学习的持续加强学习算法，使用他们以前任务的经验更快地学习新任务。我们介绍了一种新的方法，连续的元策略搜索（Comps），通过以增量方式，在序列中的每个任务上，通过序列的每个任务来消除此限制，而无需重新访问先前的任务。 Comps持续重复两个子程序：使用RL学习新任务，并使用RL的经验完全离线Meta学习，为后续任务学习做好准备。我们发现，在若干挑战性连续控制任务的旧序列上，Comps优于持续的持续学习和非政策元增强方法。

A long-standing challenge in artificial intelligence is lifelong learning. In lifelong learning, many tasks are presented in sequence and learners must efficiently transfer knowledge between tasks while avoiding catastrophic forgetting over long lifetimes. On these problems, policy reuse and other multi-policy reinforcement learning techniques can learn many tasks. However, they can generate many temporary or permanent policies, resulting in memory issues. Consequently, there is a need for lifetime-scalable methods that continually refine a policy library of a pre-defined size. This paper presents a first approach to lifetime-scalable policy reuse. To pre-select the number of policies, a notion of task capacity, the maximal number of tasks that a policy can accurately solve, is proposed. To evaluate lifetime policy reuse using this method, two state-of-the-art single-actor base-learners are compared: 1) a value-based reinforcement learner, Deep Q-Network (DQN) or Deep Recurrent Q-Network (DRQN); and 2) an actor-critic reinforcement learner, Proximal Policy Optimisation (PPO) with or without Long Short-Term Memory layer. By selecting the number of policies based on task capacity, D(R)QN achieves near-optimal performance with 6 policies in a 27-task MDP domain and 9 policies in an 18-task POMDP domain; with fewer policies, catastrophic forgetting and negative transfer are observed. Due to slow, monotonic improvement, PPO requires fewer policies, 1 policy for the 27-task domain and 4 policies for the 18-task domain, but it learns the tasks with lower accuracy than D(R)QN. These findings validate lifetime-scalable policy reuse and suggest using D(R)QN for larger and PPO for smaller library sizes.

在线持续学习是一个充满挑战的学习方案，模型必须从非平稳的数据流中学习，其中每个样本只能看到一次。主要的挑战是在避免灾难性遗忘的同时逐步学习，即在从新数据中学习时忘记先前获得的知识的问题。在这种情况下，一种流行的解决方案是使用较小的内存来保留旧数据并随着时间的推移进行排练。不幸的是，由于内存尺寸有限，随着时间的推移，内存的质量会恶化。在本文中，我们提出了OLCGM，这是一种基于新型重放的持续学习策略，该策略使用知识冷凝技术连续压缩记忆并更好地利用其有限的尺寸。样品冷凝步骤压缩了旧样品，而不是像其他重播策略那样将其删除。结果，实验表明，每当与数据的复杂性相比，每当记忆预算受到限制，OLCGM都会提高与最先进的重播策略相比的最终准确性。

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

持续学习研究的主要重点领域是通过设计新算法对分布变化更强大的新算法来减轻神经网络中的“灾难性遗忘”问题。尽管持续学习文献的最新进展令人鼓舞，但我们对神经网络的特性有助于灾难性遗忘的理解仍然有限。为了解决这个问题，我们不关注持续的学习算法，而是在这项工作中专注于模型本身，并研究神经网络体系结构对灾难性遗忘的“宽度”的影响，并表明宽度在遗忘遗产方面具有出人意料的显着影响。为了解释这种效果，我们从各个角度研究网络的学习动力学，例如梯度正交性，稀疏性和懒惰的培训制度。我们提供了与不同架构和持续学习基准之间的经验结果一致的潜在解释。

Progress in continual reinforcement learning has been limited due to several barriers to entry: missing code, high compute requirements, and a lack of suitable benchmarks. In this work, we present CORA, a platform for Continual Reinforcement Learning Agents that provides benchmarks, baselines, and metrics in a single code package. The benchmarks we provide are designed to evaluate different aspects of the continual RL challenge, such as catastrophic forgetting, plasticity, ability to generalize, and sample-efficient learning. Three of the benchmarks utilize video game environments (Atari, Procgen, NetHack). The fourth benchmark, CHORES, consists of four different task sequences in a visually realistic home simulator, drawn from a diverse set of task and scene parameters. To compare continual RL methods on these benchmarks, we prepare three metrics in CORA: Continual Evaluation, Isolated Forgetting, and Zero-Shot Forward Transfer. Finally, CORA includes a set of performant, open-source baselines of existing algorithms for researchers to use and expand on. We release CORA and hope that the continual RL community can benefit from our contributions, to accelerate the development of new continual RL algorithms.

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

恶意软件（恶意软件）分类为持续学习（CL）制度提供了独特的挑战，这是由于每天收到的新样本的数量以及恶意软件的发展以利用新漏洞。在典型的一天中，防病毒供应商将获得数十万个独特的软件，包括恶意和良性，并且在恶意软件分类器的一生中，有超过十亿个样品很容易积累。鉴于问题的规模，使用持续学习技术的顺序培训可以在减少培训和存储开销方面提供可观的好处。但是，迄今为止，还没有对CL应用于恶意软件分类任务的探索。在本文中，我们研究了11种应用于三个恶意软件任务的CL技术，涵盖了常见的增量学习方案，包括任务，类和域增量学习（IL）。具体而言，使用两个现实的大规模恶意软件数据集，我们评估了CL方法在二进制恶意软件分类（domain-il）和多类恶意软件家庭分类（Task-IL和类IL）任务上的性能。令我们惊讶的是，在几乎所有情况下，持续的学习方法显着不足以使训练数据的幼稚关节重播 - 在某些情况下，将精度降低了70个百分点以上。与关节重播相比，有选择性重播20％的存储数据的一种简单方法可以实现更好的性能，占训练时间的50％。最后，我们讨论了CL技术表现出乎意料差的潜在原因，希望它激发进一步研究在恶意软件分类域中更有效的技术。

增量任务学习（ITL）是一个持续学习的类别，试图培训单个网络以进行多个任务（一个接一个），其中每个任务的培训数据仅在培训该任务期间可用。当神经网络接受较新的任务培训时，往往会忘记旧任务。该特性通常被称为灾难性遗忘。为了解决此问题，ITL方法使用情节内存，参数正则化，掩盖和修剪或可扩展的网络结构。在本文中，我们提出了一个基于低级别分解的新的增量任务学习框架。特别是，我们表示每一层的网络权重作为几个等级1矩阵的线性组合。为了更新新任务的网络，我们学习一个排名1（或低级别）矩阵，并将其添加到每一层的权重。我们还引入了一个其他选择器向量，该向量将不同的权重分配给对先前任务的低级矩阵。我们表明，就准确性和遗忘而言，我们的方法的表现比当前的最新方法更好。与基于情节的内存和基于面具的方法相比，我们的方法还提供了更好的内存效率。我们的代码将在https://github.com/csiplab/task-increment-rank-update.git上找到。

AI的一个关键挑战是构建体现的系统，该系统在动态变化的环境中运行。此类系统必须适应更改任务上下文并持续学习。虽然标准的深度学习系统实现了最先进的静态基准的结果，但它们通常在动态方案中挣扎。在这些设置中，来自多个上下文的错误信号可能会彼此干扰，最终导致称为灾难性遗忘的现象。在本文中，我们将生物学启发的架构调查为对这些问题的解决方案。具体而言，我们表明树突和局部抑制系统的生物物理特性使网络能够以特定于上下文的方式动态限制和路由信息。我们的主要贡献如下。首先，我们提出了一种新颖的人工神经网络架构，该架构将活跃的枝形和稀疏表示融入了标准的深度学习框架中。接下来，我们在需要任务的适应性的两个单独的基准上研究这种架构的性能：Meta-World，一个机器人代理必须学习同时解决各种操纵任务的多任务强化学习环境;和一个持续的学习基准，其中模型的预测任务在整个训练中都会发生变化。对两个基准的分析演示了重叠但不同和稀疏的子网的出现，允许系统流动地使用最小的遗忘。我们的神经实现标志在单一架构上第一次在多任务和持续学习设置上取得了竞争力。我们的研究揭示了神经元的生物学特性如何通知深度学习系统，以解决通常不可能对传统ANN来解决的动态情景。