Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi -- a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, and benchmark state-of-the-art LLL algorithms in limited memory and computation regimes to shed light on their strengths and weaknesses. This continual learning paradigm also provides us with a pragmatic way of going beyond centralized training which is the most commonly used training protocol in MARL. We empirically show that the agents trained in our setup are able to coordinate well with unseen agents, without any additional assumptions made by previous works. The code and all pre-trained models are available at https://github.com/chandar-lab/Lifelong-Hanabi.
Online few-shot learning describes a setting where models are trained and evaluated on a stream of data while learning emerging classes. While prior work in this setting has achieved very promising performance on instance classification when learning from data-streams composed of a single indoor environment, we propose to extend this setting to consider object classification on a series of several indoor environments, which is likely to occur in applications such as robotics. Importantly, our setting, which we refer to as online few-shot continual learning, injects the well-studied issue of ca…
University of Amsterdam（阿姆斯特丹大学）；Facebook AI（脸书人工智能研究院）；King’s College London（伦敦国王学院）
Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning paradigm; however, when used to learn a sequence of tasks, they fail to retain past knowledge and learn incrementally. We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay that directly optimizes to prevent forgetting. We show that under the realistic setting of performing a single pass on a st…
Georgia Tech（佐治亚理工学院）；University of Cambridge（剑桥大学）；MPI-IS（马克斯·普朗克智能系统研究所）
In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample efficiency. We consider the setting where all target tasks can be represented in the span of a small number of unknown linear or nonlinear features of the input data. We propose a lifelong learning algorithm that maintains and refines the internal feature representation. We prove that for any desired accuracy on all tasks, the dimension of the representation remains close to t…
IBM Research（IBM研究）；T.J. Watson Research Center（T.J.沃森研究中心）
Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong learning system must have three key capabilities: it must learn and adapt over time, it must not forget what it has learned, and it must be efficient in both training time and memory. Recent techniques have focused their efforts primarily on the first two capabil…
University of Oxford（牛津大学）；Facebook AI Research（脸书人工智能研究院）
In lifelong learning, the learner is presented with a sequence of tasks, incrementally building a data-driven prior which may be leveraged to speed up learning of a new task. In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost. Towards this end, we first introduce a new and a more realistic evaluation protocol, whereby learners observe each example only once and hyper-parameter selection is done on a small and disjoint set of tasks, which is not used for the actual learning experience and evaluation. Second, w…
University of Southern California（南加州大学）；Tsinghua University（清华大学）
The multi-agent path-finding (MAPF) problem has recently received a lot of attention. However, it does not capture important characteristics of many real-world domains, such as automated warehouses, where agents are constantly engaged with new tasks. In this paper, we therefore study a lifelong version of the MAPF problem, called the multi-agent pickup and delivery (MAPD) problem. In the MAPD problem, agents have to attend to a stream of delivery tasks in an online setting. One agent has to be assigned to each delivery task. This agent has to first move to a given pickup location and then to a…
Enhancing Lifelong Multi-Agent Path Finding with Cache Mechanism
University of Southern California（南加州大学）；University of Wisconsin–Madison（威斯康星大学麦迪逊分校）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Irvine（加州大学欧文分校）
Vrije Universiteit Brussel（布鲁塞尔自由大学）；HU University of Applied Sciences（HU应用科学大学）
Multi-agent coordination is prevalent in many real-world applications. However, such coordination is challenging due to its combinatorial nature. An important observation in this regard is that agents in the real world often only directly affect a limited set of neighbouring agents. Leveraging such loose couplings among agents is key to making coordination in multi-agent systems feasible. In this work, we focus on learning to coordinate. Specifically, we consider the multi-agent multi-armed bandit framework, in which fully cooperative loosely-coupled agents must learn to coordinate their decis…
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
University of California, Los Angeles（加州大学洛杉矶分校）；Niantic Labs（Niantic实验室）；Apple Inc.（苹果公司）；Northwestern University（西北大学）；University of Maryland, College Park（马里兰大学帕克分校）
Politecnico di Milano（米兰理工大学）；University of Padova（帕多瓦大学）
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 approach which learns a hyper-policy, whose input is time, that outputs the parameters of the policy to be queried at that time. This hyper-policy is trained to maximize the estimated future performance, efficiently reusing past data by means of importance sampling, at the cost of introducing a controlled bias. We combine the future performance estimate with the …
As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms tha…
Robotics Institute, School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院机器人研究所）；School of Earth Sciences, Ohio State University（俄亥俄州立大学地球科学学院）
The active search for objects of interest in an unknown environment has many robotics applications including search and rescue, detecting gas leaks or locating animal poachers. Existing algorithms often prioritize the location accuracy of objects of interest while other practical issues such as the reliability of object detection as a function of distance and lines of sight remain largely ignored. Additionally, in many active search scenarios, communication infrastructure may be unreliable or unestablished, making centralized control of multiple agents impractical. We present an algorithm call…
Intelligent behaviour in the physical world exhibits structure at multiple spatial and temporal scales. Although movements are ultimately executed at the level of instantaneous muscle tensions or joint torques, they must be selected to serve goals defined on much longer timescales, and in terms of relations that extend far beyond the body itself, ultimately involving coordination with other agents. Recent research in artificial intelligence has shown the promise of learning-based approaches to the respective problems of complex movement, longer-term planning and multi-agent coordination. Howev…
Visual Heading Prediction for Autonomous Aerial Vehicles
Department of Computer Science at North Carolina A&T State University（北卡罗来纳A&T州立大学计算机科学系）；Department of Electrical and Computer Engineering at North Carolina A&T State University（北卡罗来纳A&T州立大学电气与计算机工程系）
University of California Berkeley（加州大学伯克利分校）；Caltech（加州理工学院）
We study the problem of online learning in competitive settings in the context of two-sided matching markets. In particular, one side of the market, the agents, must learn about their preferences over the other side, the firms, through repeated interaction while competing with other agents for successful matches. We propose a class of decentralized, communication- and coordination-free algorithms that agents can use to reach to their stable match in structured matching markets. In contrast to prior works, the proposed algorithms make decisions based solely on an agent's own history of play and…
Due to the increasing popularity of electric vehicles (EVs) and the technological advancement of EV electronics, the vehicle-to-grid (V2G) technique and large-scale scheduling algorithms have been developed to achieve a high level of renewable energy and power grid stability. This paper proposes a deep reinforcement learning (DRL) method for the continuous charging/discharging coordination strategy in aggregating large-scale EVs in V2G mode with renewable energy sources (RES). The DRL coordination strategy can efficiently optimize the electric vehicle aggregator's (EVA's) real-time charging/di…
National University of Ireland Galway（爱尔兰国立高威大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；HU University of Applied Sciences Utrecht（乌得勒支应用科学大学）
Many real-world problems contain multiple objectives and agents, where a trade-off exists between objectives. Key to solving such problems is to exploit sparse dependency structures that exist between agents. For example, in wind farm control a trade-off exists between maximising power and minimising stress on the systems components. Dependencies between turbines arise due to the wake effect. We model such sparse dependencies between agents as a multi-objective coordination graph (MO-CoG). In multi-objective reinforcement learning a utility function is typically used to model a users preferenc…
