Many real-world tasks involve multiple agents with partial observability and limited communication. Learning is challenging in these settings due to local viewpoints of agents, which perceive the world as non-stationary due to concurrently-exploring teammates. Approaches that learn specialized policies for individual tasks face problems when applied to the real world: not only do agents have to learn and store distinct policies for each task, but in practice identities of tasks are often non-observable, making these approaches inapplicable. This paper formalizes and addresses the problem of multi-task multi-agent reinforcement learning under partial observability. We introduce a decentralized single-task learning approach that is robust to concurrent interactions of teammates, and present an approach for distilling single-task policies into a unified policy that performs well across multiple related tasks, without explicit provision of task identity.
University of Georgia（佐治亚大学）；University of Southern Mississippi（南密西西比大学）
Recent renewed interest in multi-agent reinforcement learning (MARL) has generated an impressive array of techniques that leverage deep reinforcement learning, primarily actor-critic architectures, and can be applied to a limited range of settings in terms of observability and communication. However, a continuing limitation of much of this work is the curse of dimensionality when it comes to representations based on joint actions, which grow exponentially with the number of agents. In this paper, we squarely focus on this challenge of scalability. We apply the key insight of action anonymity, …
In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state. Asymmetric actor-critic methods exploit such information by training a history-based policy via a state-based critic. However, many asymmetric methods lack theoretical foundation, and are only evaluated on limited domains. We examine the theory of asymmetric actor-critic methods which use state-based critics, and expose fundamental issues which undermine the validity of a common variant, and limit its abili…
TU Darmstadt（达姆施塔特工业大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；Aalto University（阿尔托大学）
Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems. However, an open question is how to make RL cope with partial observability which is prevalent in many real-world problems. Contrary to contemporary RL approaches, which focus mostly on improved memory representations or strong assumptions about the type of partial observability, we propose a simple but efficient approach that can be applied together with a wide variety of RL methods. Our main insight is that smoothly transitioning from full obser…
Silicon Austria Labs（奥地利硅实验室）；Graz University of Technology（格拉茨技术大学）
In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's precise interaction with its environment. Therefore, we propose an approach for reinforcement learning (RL) in partially observable environments. While assuming that the environment behaves like a partially observable Markov decision process with known discrete actions, we assume no knowledge about its structure or transition probabilities. Our approach combines Q-learning with IoAlergia, a method for learning Markov de…
Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability
Bosch Corporate Research（博世企业研究院）；Technical University Darmstadt（达姆施塔特工业大学）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Centre for Cognitive Science（认知科学中心）
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；DeepMind（深度思维）；Massachusetts Institute of Technology（麻省理工学院）
Multi-agent reinforcement learning (MARL) algorithms often suffer from an exponential sample complexity dependence on the number of agents, a phenomenon known as \emph{the curse of multiagents}. In this paper, we address this challenge by investigating sample-efficient model-free algorithms in \emph{decentralized} MARL, and aim to improve existing algorithms along this line. For learning (coarse) correlated equilibria in general-sum Markov games, we propose \emph{stage-based} V-learning algorithms that significantly simplify the algorithmic design and analysis of recent works, and circumvent a…
UM-SJTU Joint Institute, Shanghai Jiao Tong University（上海交通大学密西根学院）；Shanghai Jiao Tong University（上海交通大学）
We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can a…
McGill University（麦吉尔大学）；University of Liege（列日大学）
This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability. Our theoretical analysis formally characterizes that while potentially increasing the asymptotic bias, a smaller state representation decreases the risk of overfitting. This analysis relies on expressing the quality of a state representation by bounding L1 error terms of the associated belief states. Theoretical results are empirically illustrated when the s…
Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approac…
Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks
Army Research Laboratory（陆军研究实验室）；U.S. Army DEVCOM Adelphi（美国陆军阿德福尔德 DEVCOM）；Industrial Engineering Dept. Purdue University（工业工程系 帕克维尔大学）；Oden Institute University of Texas, Austin（奥登研究所 德州大学奥斯汀）
In the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches starts with no initial knowledge of the environment. We propose the use of a multi-agent reinforcement learning (MARL) paradigm for a spatially formulated decentralized two-sided matching market with independent and autonomous agents. Having autonomous agents acting independently makes our environment very dynamic and uncertain. Moreover, agents lack the knowledge of preferences of other agents and have to explore th…
Peking University（北京大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees $\varepsilon$-convergence at each turn, their joint…
The University of Melbourne（墨尔本大学）；Defence Science and Technology Group, Australian Department of Defence（澳大利亚国防部国防科技集团）
Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies the problem in the context of computer vision or console games, this paper focuses on reinforcement learning in autonomous cyber defence under partial observability. We demonstrate that under the black-box setting, where the attacker has no direct access to the target RL model, causative attacks---attacks that target the training process---can poison RL agents…
School of Informatics（信息学院）；University of Edinburgh（爱丁堡大学）
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from the local information of the controlled agent using encoder-decoder architectures. Using the observations and actions of the modelled agents during training, our models learn to extract representations about the modelled agents conditioned only on the local observa…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）；The Hong Kong University of Science and Technology（香港科技大学）
Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents. Specifically, we consider two decentralized MARL settings, where teams of agents are connected by time-varying communication networks, and either collaborate or compete in a zero-sum game setting, without any central controller. These settings cover many conventional MARL setti…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper addresses the problem of learning an equilibrium efficiently in general-sum Markov games through decentralized multi-agent reinforcement learning. Given the fundamental difficulty of calculating a Nash equilibrium (NE), we instead aim at finding a coarse correlated equilibrium (CCE), a solution concept that generalizes NE by allowing possible correlations among the agents' strategies. We propose an algorithm in which each agent independently runs optimistic V-learning (a variant of Q-learning) to efficiently explore the unknown environment, while using a stabilized online mirror des…
[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We extend those results to offer a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces. Deterministic policies are important in real-world settings. To handle the lack of exploration inherent in deterministic policies, we consider both off-policy and on-policy settings. We provide the expressio…
Assessing the systemic effects of uncertainty that arises from agents' partial observation of the true states of the world is critical for understanding a wide range of scenarios. Yet, previous modeling work on agent learning and decision-making either lacks a systematic way to describe this source of uncertainty or puts the focus on obtaining optimal policies using complex models of the world that would impose an unrealistically high cognitive demand on real agents. In this work we aim to efficiently describe the emergent behavior of biologically plausible and parsimonious learning agents fac…
Multi-Agent Reinforcement Learning (MARL) is a challenging subarea of Reinforcement Learning due to the non-stationarity of the environments and the large dimensionality of the combined action space. Deep MARL algorithms have been applied to solve different task offloading problems. However, in real-world applications, information required by the agents (i.e. rewards and states) are subject to noise and alterations. The stability and the robustness of deep MARL to practical challenges is still an open research problem. In this work, we apply state-of-the art MARL algorithms to solve task offlo…
A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when exploration is fully decentralized. Specifically, we consider a class of online, episodic, tabular $Q$-learning problems under time-varying reward and transition dynamics, in which agents can communicate in a decentralized manner.We show that group performance, as measured by the bound on regret, can be significantly improved through communication when each…
Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
The Ohio State University, Columbus, Ohio, USA（俄亥俄州立大学）；University of Wisconsin-Whitewater, Whitewater, Wisconsin, USA（威斯康星大学-威奇托分校）；University of Colorado Boulder, Boulder, Colorado, USA（科罗拉多大学博尔德分校）
University of Science and Technology of China（中国科学技术大学）；Huawei Cloud（华为云）
Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has become one of the most widely used MARL paradigms. In CTDE, centralized information is dedicated to learning the allocation of the team reward with a mixing network, while the learning of individual Q-values is usually based on local observations. The insufficient utility of global observation will degrade performance in challenging environments. To this end, this work proposes a novel Centralized Teacher with Decen…
Collaboration requires agents to align their goals on the fly. Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous. Starting with pretrained, single-agent point to point navigation policies and using noisy, high-dimensional sensor inputs like lidar, we first learn via self-supervision motion predictions of all agents on the team. Next, HPP uses the prediction mod…
University of Delaware（特拉华大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
Recent multi-agent actor-critic methods have utilized centralized training with decentralized execution to address the non-stationarity of co-adapting agents. This training paradigm constrains learning to the centralized phase such that only pre-learned policies may be used during the decentralized phase, which performs poorly when agent communications are delayed, noisy, or disrupted. In this work, we propose a new system that can gracefully handle partially-observable information due to communication disruptions during decentralized execution. Our approach augments the multi-agent actor-crit…
We discuss the problem of decentralized multi-agent reinforcement learning (MARL) in this work. In our setting, the global state, action, and reward are assumed to be fully observable, while the local policy is protected as privacy by each agent, and thus cannot be shared with others. There is a communication graph, among which the agents can exchange information with their neighbors. The agents make individual decisions and cooperate to reach a higher accumulated reward. Towards this end, we first propose a decentralized actor-critic (AC) setting. Then, the policy evaluation and policy improv…
F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；Tongji University（同济大学）；Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）
In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact their reward, to specific states and deliberately avoid them. The situation is particularly challenging in a multi-agent context because agents might not only learn from their own past interruptions, but also from those of other agents. Orseau and Armstrong defined \emph{safe interr…
SRM Institute of Science and Technology（SRM科学技术学院）
This work presents a decentralized motion planning framework for addressing the task of multi-robot navigation using deep reinforcement learning. A custom simulator was developed in order to experimentally investigate the navigation problem of 4 cooperative non-holonomic robots sharing limited state information with each other in 3 different settings. The notion of decentralized motion planning with common and shared policy learning was adopted, which allowed robust training and testing of this approach in a stochastic environment since the agents were mutually independent and exhibited asynch…
Mechanical and Industrial Engineering Department, Northeastern University（东北大学机械与工业工程学院）
Targets search and detection encompasses a variety of decision problems such as coverage, surveillance, search, observing and pursuit-evasion along with others. In this paper we develop a multi-agent deep reinforcement learning (MADRL) method to coordinate a group of aerial vehicles (drones) for the purpose of locating a set of static targets in an unknown area. To that end, we have designed a realistic drone simulator that replicates the dynamics and perturbations of a real experiment, including statistical inferences taken from experimental data for its modeling. Our reinforcement learning m…
We propose the first model-free algorithm that achieves low regret performance for decentralized learning in two-player zero-sum tabular stochastic games with infinite-horizon average-reward objective. In decentralized learning, the learning agent controls only one player and tries to achieve low regret performances against an arbitrary opponent. This contrasts with centralized learning where the agent tries to approximate the Nash equilibrium by controlling both players. In our infinite-horizon undiscounted setting, additional structure assumptions is needed to provide good behaviors of learn…
Johnson Controls Inc.（江森自控有限公司）；Iowa State University（爱荷华州立大学）；New York University（纽约大学）
We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. Moreover, MDPGT provably achieves the best available sample complexity of $\mathca…
Khoury College of Computer Sciences（Khoury计算机科学学院）；Northeastern University（东北大学）
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that uses a fully observable policy (which we call a state expert) during offline training to improve online performance. Based on Soft Actor-Critic (SAC), our agent balances performing actions similar to the state expert and getting high returns under partial observability. Our approach can leverage the f…
Dorabot Inc.（达闼机器人有限公司）；Fuzhou University（福州大学）；City University of Hong Kong（香港城市大学）
Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed multi-robot collision avoidance systems exist, they often require extracting agent-level features to plan a local collision-free action, which can be computationally prohibitive and not robust. More importantly, in practice the performance of these methods are much lower than their centralized counterparts. We present a decentralized sensor-level collision avoi…
Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning
University of Warsaw（华沙大学）；IDEAS Research Institute（IDEAS研究机构）；Institute of Fundamental Technological Research, Polish Academy of Sciences（波兰科学院基础技术研究所）；IDEAS NCBR；Warsaw University of Technology（华沙技术大学）
