In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We begin by discussing our perspective on why RL is a natural fit for studying continual learning. We then provide a taxonomy of different continual RL formulations by mathematically characterizing two key properties of non-stationarity, namely, the scope and driver non-stationarity. This offers a unified view of various formulations. Next, we review and present a taxonomy of continual RL approaches. We go on to discuss evaluation of continual RL agents, providing an overview of benchmarks used in the literature and important metrics for understanding agent performance. Finally, we highlight open problems and challenges in bridging the gap between the current state of continual RL and findings in neuroscience. While still in its early days, the study of continual RL has the promise to develop better incremental reinforcement learners that can function in increasingly realistic applications where non-stationarity plays a vital role. These include applications such as those in the fields of healthcare, education, logistics, and robotics.
The Effectiveness of World Models for Continual Reinforcement Learning
University of Oxford（牛津大学）；Warsaw University of Technology（华沙理工大学）；Jagiellonian University（雅盖隆大学）；Polish Academy of Sciences（波兰科学院）；Institute of Theoretical and Applied Informatics, PAS（波兰科学院理论与应用信息研究所）
Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；Allen Institute for AI（艾伦人工智能研究所）
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, Proc…
We have developed a model for online continual or lifelong reinforcement learning (RL) inspired on the insect brain. Our model leverages the offline training of a feature extraction and a common general policy layer to enable the convergence of RL algorithms in online settings. Sharing a common policy layer across tasks leads to positive backward transfer, where the agent continuously improved in older tasks sharing the same underlying general policy. Biologically inspired restrictions to the agent's network are key for the convergence of RL algorithms. This provides a pathway towards efficien…
Continual Learning as Computationally Constrained Reinforcement Learning
Department of Computer Science, Stanford University（计算机科学系，斯坦福大学）；Department of Electrical Engineering, Stanford University（电气工程系，斯坦福大学）；Department of Management Science and Engineering, Stanford University（管理科学与工程系，斯坦福大学）
Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanche RL, a library for Continual Reinforcement Learning which allows to easily train agents on a continuous stream of tasks. Avalanche RL is based on PyTorch and supports any OpenAI Gym environment. Its design is based on Avalanche, one of the more popular continual learning libraries, which allow us to reuse a large number of continual learning strategies and improve the interact…
University of Alberta（阿尔伯塔大学）；Google DeepMind（谷歌DeepMind）；CIFAR AI（CIFAR人工智能研究院）
Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they often change the optimizer or the architecture, a complexity that hinders widespread adoption in various systems. In this paper, we focus on learning failures that are associated with increasing weight norm and we propose a simple technique that can be easily added on top of existing learning systems: clipping neural network weights to limit them to a specific…
DeepMind（深度思维）；Harvard University（哈佛大学）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））
The ability to learn continually is essential in a complex and changing world. In this paper, we characterize the behavior of canonical value-based deep reinforcement learning (RL) approaches under varying degrees of non-stationarity. In particular, we demonstrate that deep RL agents lose their ability to learn good policies when they cycle through a sequence of Atari 2600 games. This phenomenon is alluded to in prior work under various guises -- e.g., loss of plasticity, implicit under-parameterization, primacy bias, and capacity loss. We investigate this phenomenon closely at scale and analy…
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；Sun Yat-sen University（中山大学）；Lehigh University（里海大学）；College of Computing and Data Science, NTU（南洋理工大学计算与数据科学学院）
Jagiellonian University（雅盖隆大学）；DeepMind；Polish Academy of Sciences（波兰科学院）；University of Oxford（牛津大学）
Continual learning (CL) -- the ability to continuously learn, building on previously acquired knowledge -- is a natural requirement for long-lived autonomous reinforcement learning (RL) agents. While building such agents, one needs to balance opposing desiderata, such as constraints on capacity and compute, the ability to not catastrophically forget, and to exhibit positive transfer on new tasks. Understanding the right trade-off is conceptually and computationally challenging, which we argue has led the community to overly focus on catastrophic forgetting. In response to these issues, we advo…
Johns Hopkins University Applied Physics Lab（约翰斯·霍普金斯大学应用物理实验室）
Training reinforcement learning agents that continually learn across multiple environments is a challenging problem. This is made more difficult by a lack of reproducible experiments and standard metrics for comparing different continual learning approaches. To address this, we present TELLA, a tool for the Test and Evaluation of Lifelong Learning Agents. TELLA provides specified, reproducible curricula to lifelong learning agents while logging detailed data for evaluation and standardized analysis. Researchers can define and share their own curricula over various learning environments or run …
Facebook AI Research（Facebook人工智能研究院）；McGill University（麦吉尔大学）；UC Berkeley（加州大学伯克利分校）
In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationary. This assumption of stationarity, while simplifying, can be unrealistic in many scenarios. In the continual reinforcement learning scenario, the sequence of tasks is another source of nonstationarity. In this work, we propose to examine this continual reinforcement learning setting through the block contextual MDP (BC-MDP) framework, which enables us to relax the assumption of stationarity. This framework challenges RL algorithms to handle both nonstati…
Imperial College London（帝国理工学院）；Google DeepMind（谷歌DeepMind）
Unlike humans, who are capable of continual learning over their lifetimes, artificial neural networks have long been known to suffer from a phenomenon known as catastrophic forgetting, whereby new learning can lead to abrupt erasure of previously acquired knowledge. Whereas in a neural network the parameters are typically modelled as scalar values, an individual synapse in the brain comprises a complex network of interacting biochemical components that evolve at different timescales. In this paper, we show that by equipping tabular and deep reinforcement learning agents with a synaptic model t…
TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）
In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent. The basic MTR buffer comprises a cascade of sub-buffers that accumulate experiences at different timescales, enabling the agent to improve the trade-off between adaptation to new data and retention of old knowledge. We also combine the MTR framework with invariant risk minimization, with the idea of encouraging the agent to learn a policy that is robust across the various envir…
Jagiellonian University（雅盖隆大学）；DeepMind（深度思维）；Polish Academy of Sciences（波兰科学院）；Ideas NCBR（Ideas国家研究与发展中心）
The ability of continual learning systems to transfer knowledge from previously seen tasks in order to maximize performance on new tasks is a significant challenge for the field, limiting the applicability of continual learning solutions to realistic scenarios. Consequently, this study aims to broaden our understanding of transfer and its driving forces in the specific case of continual reinforcement learning. We adopt SAC as the underlying RL algorithm and Continual World as a suite of continuous control tasks. We systematically study how different components of SAC (the actor and the critic,…
ENSTA Paris（巴黎高等先进技术学院）；Institute Polytechnique de Paris（巴黎理工学院）；INRIA（法国国家信息与自动化研究所）；Softbank Robotics Europe（软银机器人欧洲公司）；Thales（泰雷兹集团）
In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-…
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）；Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University（山西大学计算机与信息技术学院，教育部计算智能与中文信息处理重点实验室）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；College of Data Science and Computing, Nanyang Technological University（南洋理工大学数据科学与计算学院）
Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）
The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries, and thus depend on human supervision. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a modular architecture designed to avoid catastrophic forgetting without making any such assumptions. At the beginning of each trajectory, a module in the SANE ensemble is activated to determine the agent'…
Continual Learning (CL) considers the problem of training an agent sequentially on a set of tasks while seeking to retain performance on all previous tasks. A key challenge in CL is catastrophic forgetting, which arises when performance on a previously mastered task is reduced when learning a new task. While a variety of methods exist to combat forgetting, in some cases tasks are fundamentally incompatible with each other and thus cannot be learnt by a single policy. This can occur, in reinforcement learning (RL) when an agent may be rewarded for achieving different goals from the same observa…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be later accessed by down-stream tasks in order to make their execution more efficient. In this work, we introduce the neural architecture with shared episodic memory (SEM) for learning and the sequential execution of multiple tasks. We explicitly split the encoding of episodic memory and task-specific memory into separate recurrent sub-networks. An agent augmented with SEM was ab…
Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning
University of Maryland College Park（马里兰大学帕克分校）；University of Granada（格拉纳达大学）；Granada AI Lab（格拉纳达人工智能实验室）；DaSCI Andalusian Institute in Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；TECNALIA（TECNALIA 技术研究院）；Basque Research & Technology Alliance (BRTA)（巴斯克研究与技术联盟）；University of the Basque Country (UPV/EHU)（巴斯克大学）
Heinrich Heine University Düsseldorf（杜塞尔多夫海因里希·海涅大学）
Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the capability to continually learn, dynamically adapting to new challenges while preserving the knowledge it already acquired. Despite the importance, continual reinforcement learning of the dialogue policy has remained largely unaddressed. The lack of a framework with training protocols, baseline models and suitable metrics, has so far hindered research in this dir…
Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning
Department of Electrical and Computer Engineering (ECE), Seoul National University（电子与计算机工程系，首尔国立大学）；Interdisciplinary Program in Artificial Intelligence (IPAI), Seoul National University（人工智能交叉计划，首尔国立大学）；Samsung Advanced Institute of Technology（三星先进技术研究所）
Berkeley AI Research（伯克利人工智能研究院）；Stanford（斯坦福大学）；Mila（米拉人工智能研究院）
We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforcement learning algorithms have demonstrated promising results in accelerating the acquisition of new tasks. However, they require access to all tasks during training. Beyond simply transferring past experience to new tasks, our goal is to devise continual reinforcement learning algorithms that learn to learn, using their experience on previous tasks to learn new tasks more quic…
