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 observations of the controlled agent. The representations are used to augment the controlled agent's decision policy which is trained via deep reinforcement learning; thus, during execution, the policy does not require access to other agents' information. We provide a comprehensive evaluation and ablations studies in cooperative, competitive and mixed multi-agent environments, showing that our method achieves higher returns than baseline methods which do not use the learned representations.
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…
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…
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, …
MIT（麻省理工学院）；Northeastern University（东北大学）；Boeing Research & Technology（波音研究与技术）
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 mu…
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…
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…
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）
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…
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…
The University of Tokyo（东京大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所革新智能综合研究中心）
Reinforcement Learning (RL), among other learning-based methods, represents powerful tools to solve complex robotic tasks (e.g., actuation, manipulation, navigation, etc.), with the need for real-world data to train these systems as one of its most important limitations. The use of simulators is one way to address this issue, yet knowledge acquired in simulations does not work directly in the real-world, which is known as the sim-to-real transfer problem. While previous works focus on the nature of the images used as observations (e.g., textures and lighting), which has proven useful for a sim…
We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective strategy. Here, a good strategy successfully counters the opponent's current and possible future strategies which can only be estimated using partial observations. We investigate whether we can utilize the full game state information during training time (in the form of an auxiliary prediction task) to increase performance. Experiments carried out within a StarCraft: Brood War…
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）
INESC-ID（里斯本系统与计算机工程研究所）；Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；Zebra Technologies（斑马技术公司）
In a warehouse environment, tasks appear dynamically. Consequently, a task management system that matches them with the workforce too early (e.g., weeks in advance) is necessarily sub-optimal. Also, the rapidly increasing size of the action space of such a system consists of a significant problem for traditional schedulers. Reinforcement learning, however, is suited to deal with issues requiring making sequential decisions towards a long-term, often remote, goal. In this work, we set ourselves on a problem that presents itself with a hierarchical structure: the task-scheduling, by a centralise…
Many real-world reinforcement learning problems have a hierarchical nature, and often exhibit some degree of partial observability. While hierarchy and partial observability are usually tackled separately (for instance by combining recurrent neural networks and options), we show that addressing both problems simultaneously is simpler and more efficient in many cases. More specifically, we make the initiation set of options conditional on the previously-executed option, and show that options with such Option-Observation Initiation Sets (OOIs) are at least as expressive as Finite State Controlle…
UC Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）；Facebook AI Research（脸书人工智能研究院）
Generalization is a central challenge for the deployment of reinforcement learning (RL) systems in the real world. In this paper, we show that the sequential structure of the RL problem necessitates new approaches to generalization beyond the well-studied techniques used in supervised learning. While supervised learning methods can generalize effectively without explicitly accounting for epistemic uncertainty, we show that, perhaps surprisingly, this is not the case in RL. We show that generalization to unseen test conditions from a limited number of training conditions induces implicit partia…
Federal University of Rio Grande do Sul（南里奥格兰德州联邦大学）
In reinforcement learning (RL), dealing with non-stationarity is a challenging issue. However, some domains such as traffic optimization are inherently non-stationary. Causes for and effects of this are manifold. In particular, when dealing with traffic signal controls, addressing non-stationarity is key since traffic conditions change over time and as a function of traffic control decisions taken in other parts of a network. In this paper we analyze the effects that different sources of non-stationarity have in a network of traffic signals, in which each signal is modeled as a learning agent.…
Attention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. We propose the first combination of self attention and reinforcement learning that is capable of producing significant improvements, including new state of the art results in the Arcade Learning Environment. Unlike the selective attention models used in previous attempts, which constrain the attention via preconceived notions of importance, our implementation utilises the…
MIT Lincoln Laboratory（麻省理工学院林肯实验室）；Stanford University（斯坦福大学）
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on particle and multiwalker robot environments that have characteristics such as system health, risk-taking, semi-expendable agents, continuous action spaces, and partial observab…
Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide. Instead, recently, more work has explored learning what to do from interacting with humans. So far, most of these approaches model humans as being (nosily) rational and, in particular, giving unbiased feedback. We argue that these models are too simplistic and that RL researchers need to develop more realistic human models to design and evaluate their algorithms. In particular, we argue that human models have to be personal, contextual, and dynamic. This pap…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Element AI（元素人工智能公司）
Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is efficient and optimal in fully observable environments. However, some form of memory is necessary when RL agents are faced with partial observability. In this paper, we study a lightweight approach to tackle partial observability in RL. We provide the agent with an external memory and additional actions to control what, if anything, is written to the memory. At every step, the current memory state is part of the agent'…
In this work, we develop an automated method to generate 3D human walking motion in simulation which is comparable to real-world human motion. At the core, our work leverages the ability of deep reinforcement learning methods to learn high-dimensional motor skills while being robust to variations in the environment dynamics. Our approach iterates between policy learning and parameter identification to match the real-world bio-mechanical human data. We present a thorough evaluation of the kinematics, kinetics and ground reaction forces generated by our learned virtual human agent. We also show …
McGill University（麦吉尔大学）；Quebec AI Institute (MILA)（魁北克人工智能研究所（MILA））；Université de Montréal（蒙特利尔大学）；Deepmind（深度思维（Deepmind））
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classical two-stage paradigm: first learn the environment dynamics and then plan accordingly. This approach, however, disconnects the two problems and can consequently lead to algorithms that are sample inefficient and time consuming. In this paper, we propose a novel algorithm that combines learning and planning together. Our algorithm is closely related to the spectral learning algorithm for predi…
Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. Yet, it poses a critical challenge since the scheduler needs to make real-time decisions to guarantee the delay and resource constraints simultaneously without prior information of system dynamics, which can be time-varying and hard to estimate. Moreover, many practical scenarios suffer from partial observability issues, e.g., due to sensing noise or hidden correlation. To tackle these challenges, we propose a deep reinforcement learning (D…
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL). For RL, a policy gradient approach is natural, but is sample inefficient. In this paper, we present 3 methods for reducing the number of dialogs required to optimize an RNN-based dialog policy with RL. The key idea is to maintain a second RNN which predicts the value of the current policy, and to apply experience replay to both networks. On two tasks, t…
Microsoft Research（微软研究院）；Princeton University（普林斯顿大学）
Real-world sequential decision making problems commonly involve partial observability, which requires the agent to maintain a memory of history in order to infer the latent states, plan and make good decisions. Coping with partial observability in general is extremely challenging, as a number of worst-case statistical and computational barriers are known in learning Partially Observable Markov Decision Processes (POMDPs). Motivated by the problem structure in several physical applications, as well as a commonly used technique known as "frame stacking", this paper proposes to study a new subcla…
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
School of Computer Science, University of Beihang, Beijing, China（北京航空航天大学计算机学院）；School of Computer Science, Chinese University of Hong Kong, Hongkong, China（香港中文大学计算机学院）；JD Explore Academy, Beijing, China（京东探索研究院）；North Automatic Control Institute, Taiyuan, China（太原北自动控制研究所）
Reinforcement Learning has applications in field of mechatronics, robotics, and other resource-constrained control system. Problem of resource allocation is primarily solved using traditional predefined techniques and modern deep learning methods. The drawback of predefined and most deep learning methods for resource allocation is failing to meet the requirements in cases of uncertain system environment. We can approach problem of resource allocation in uncertain system environment alongside following certain criteria using deep reinforcement learning. Also, reinforcement learning has ability …
Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms appealing for real world problems such as robot control. In practice, however, standard off-policy algorithms fail in the batch setting for continuous control. In this paper, we propose a simple solution to this problem. It admits the use of data generated by arbitrary behavior policies and uses a learned prior -- the advantage-weighted behavior model (ABM) -- to…
In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observability, their provided observation can have different levels of importance. In this paper, we present a novel attention-based deep reinforcement learning method in a multi-view environment in which each view can provide various representative information about the environment. Specifi…
