Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with state-based critics, since centralized training allows access to the true system state, which can be useful during training despite not being available at execution time. State-based critics have become a common empirical choice, albeit one which has had limited theoretical justification or analysis. In this paper, we show that state-based critics can introduce bias in the policy gradient estimates, potentially undermining the asymptotic guarantees of the algorithm. We also show that, even if the state-based critics do not introduce any bias, they can still result in a larger gradient variance, contrary to the common intuition. Finally, we show the effects of the theories in practice by comparing different forms of centralized critics on a wide range of common benchmarks, and detail how various environmental properties are related to the effectiveness of different types of critics.
EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework
Zhongguancun Academy（中关村学院）；College of Software, Nankai University（南开大学软件学院）；School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
Chalmers University of Technology（查尔姆斯理工大学）；University of Oslo（奥斯陆大学）
We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance relative to the Bayes optimal policy, with a lower computational complexity. The main novelty is the use of a candidate policy generator, to generate long-term options in the planning tree (over beliefs), which allows us to create much sparser and deeper trees. Experimental results on different environments show that in comparison to the state-of-the-art, o…
In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement learning (RL) algorithms often use small MLPs, and gains in performance typically originate from algorithmic innovations. It is natural to hypothesize that small datasets in RL necessitate simple models to avoid overfitting; however, this hypothesis is untested. In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern …
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of California Berkeley（加州大学伯克利分校）
While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for reinforcement learning remain relatively under-explored. We take inspiration from successful architectural choices in computer vision and generative modelling, and investigate the use of deeper networks and dense connections for reinforcement learning on a variety of simulated robotic learning benchmark environments. Our findings reveal that current methods benefit …
University of Oxford（牛津大学）；Microsoft Research Montreal（微软研究院蒙特利尔分院）
We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both actor and critic, i.e., there is a $γ^t$ term in the actor update for the transition observed at time $t$ in a trajectory and the critic is a discounted value function. Practitioners, however, usually ignore the discounting ($γ^t$) for the actor while using a discounted critic. We investigate this mismatch in two scenarios. In the first scenario, we consider optimizing an undiscounted objective $(γ…
Recently experience replay is widely used in various deep reinforcement learning (RL) algorithms, in this paper we rethink the utility of experience replay. It introduces a new hyper-parameter, the memory buffer size, which needs carefully tuning. However unfortunately the importance of this new hyper-parameter has been underestimated in the community for a long time. In this paper we did a systematic empirical study of experience replay under various function representations. We showcase that a large replay buffer can significantly hurt the performance. Moreover, we propose a simple O(1) meth…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution shift, and (2) representation conditions that are stronger than realizability. However, the necessity ("why do we need them?") and the naturalness ("when do they hold?") of such assumptions have largely eluded the literature. In this paper, we revisit these assumptions and provide theoretical results towards answering the above questions, and make steps towa…
Leiden Institute of Advanced Computer Science, Leiden University（莱顿大学莱顿高级计算机科学研究所）；TU Delft（代尔夫特理工大学）
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both largely have their own research communities. However, if both research fields solve the same problem, then we might be able to disentangle the common factors in their solution approaches. Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning …
Khoury College of Computer Sciences, Northeastern University（东北大学库里计算机科学学院）
Policy gradient methods have become popular in multi-agent reinforcement learning, but they suffer from high variance due to the presence of environmental stochasticity and exploring agents (i.e., non-stationarity), which is potentially worsened by the difficulty in credit assignment. As a result, there is a need for a method that is not only capable of efficiently solving the above two problems but also robust enough to solve a variety of tasks. To this end, we propose a new multi-agent policy gradient method, called Robust Local Advantage (ROLA) Actor-Critic. ROLA allows each agent to learn …
Value-based reinforcement-learning algorithms provide state-of-the-art results in model-free discrete-action settings, and tend to outperform actor-critic algorithms. We argue that actor-critic algorithms are limited by their need for an on-policy critic. We propose Bootstrapped Dual Policy Iteration (BDPI), a novel model-free reinforcement-learning algorithm for continuous states and discrete actions, with an actor and several off-policy critics. Off-policy critics are compatible with experience replay, ensuring high sample-efficiency, without the need for off-policy corrections. The actor, b…
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by using procedurally generated environments to construct distinct training and test sets. Most notably, we introduce a new environment called CoinRun, designed as a benchmark for generalization in RL. Using CoinRun, we find that agents overfit to surprisingly large training sets. We th…
University of Southern California（南加州大学）；Google AI（谷歌人工智能）
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep. This attention mechanism enables more effective and scalable learning in complex multi-agent environments, when compared to recent approaches. Our approach is applicable not only to cooperative settings with sh…
Sparebank 1 SR-Bank（Sparebank 1 SR银行）；Center for Artificial Intelligence Research（人工智能研究中心）；University of Agder（阿格德大学）
Personalisation of products and services is fast becoming the driver of success in banking and commerce. Machine learning holds the promise of gaining a deeper understanding of and tailoring to customers' needs and preferences. Whereas traditional solutions to financial decision problems frequently rely on model assumptions, reinforcement learning is able to exploit large amounts of data to improve customer modelling and decision-making in complex financial environments with fewer assumptions. Model explainability and interpretability present challenges from a regulatory perspective which dema…
Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the process of feature learning, others pretrain the policies by imitating expert demonstrations. However, these methods are unstable and not suitable for actor-critic reinforcement learning algorithms. Also, some existing methods rely on the global optimum assumption, which is not true in most scenarios. In this paper, we employ expert demonstrations in a actor-…
In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return. That is, a state in which the choice of action is more likely to influence the final outcome is considered as more critical than a state in which it is less likely to influence the final outcome. We formulate a criticality-based varying step number algorithm (CVS) - a flexible step number algorithm that utilizes the criticality function provided by a human, or learned directly from the envi…
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…
Communication is a critical factor for the big multi-agent world to stay organized and productive. Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such as tabular reinforcement learning and evolutionary algorithm, which can not generalize to changing environment or large collection of agents. In this paper, we propose an Actor-Coordinator-Critic Net (ACCNet) framework for solving "learning-to-communicate" problem. The ACCNet naturally combines the powerful actor-critic reinforcement learning technology with…
In this paper we propose a hybrid architecture of actor-critic algorithms for reinforcement learning in parameterized action space, which consists of multiple parallel sub-actor networks to decompose the structured action space into simpler action spaces along with a critic network to guide the training of all sub-actor networks. While this paper is mainly focused on parameterized action space, the proposed architecture, which we call hybrid actor-critic, can be extended for more general action spaces which has a hierarchical structure. We present an instance of the hybrid actor-critic archite…
University of Tasmania（塔斯马尼亚大学）；University of Technology Sydney（悉尼科技大学）
In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learning from hierarchical critics (RLHC) algorithm. In our approach, each agent receives value information from local and global critics regarding a competition task and accesses multiple cooperative critics in a top-down hierarchy. Thus, each agent not only receives low-level details …
McGill University（麦吉尔大学）；Mila；Deakin University（迪肯大学）；Université Laval（拉瓦尔大学）；Facebook AI Research；MSR Montreal（蒙特利尔微软研究院）；Université de Montréal（蒙特利尔大学）
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensional state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive op…
In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if the reinforcement signals received by the agent have a high variance, a significant underestimation bias arises. To minimize the underestimation, we introduce a parameter-free, novel deep Q-learning variant. Our Q-value update rule combines the notions behind Clipped Double Q-learning and Maxmin Q-learning by computing the critic objective through the nested c…
To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are adversarial reinforcement learning methods. These methods set the problem as a two-player game between the protagonist agent, which learns to perform a task in an environment, and the adversary agent, which learns to disturb the protagonist via modifications of the considered environment. Both protagonist and adversary are trained with deep reinforcement lea…
Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a large bias, while a large n leads to large variance. The literature offers no straightforward recipe for the best choice of this value. While currently all n-step algorithms use a fixed value of n over the state space we extend the framework of n-step …
Stony Brook University（石溪大学）；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）
This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. It is shown that the algorithm can solve the problem for strongly connected graphs by allowing each agent to transmit only two scalar-valued variables at one time.
DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning
Department of Automation, Tsinghua University（清华大学自动化系）；School of Engineering and Applied Science, Columbia University（哥伦比亚大学工程与应用科学学院）；School of Business, Sun Yat-sen University（中山大学商学院）；Stern School of Business, New York University（纽约大学斯特恩商学院）
SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization
Technical University of Munich（慕尼黑工业大学）；Peking University（北京大学）；BIGAI（北京通用人工智能研究院）；King's College London（伦敦国王学院）；Tongji University（同济大学）；University College London（伦敦大学学院）
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）
Deep neuroevolution and deep Reinforcement Learning have received a lot of attention in the last years. Some works have compared them, highlighting theirs pros and cons, but an emerging trend consists in combining them so as to benefit from the best of both worlds. In this paper, we provide a survey of this emerging trend by organizing the literature into related groups of works and casting all the existing combinations in each group into a generic framework. We systematically cover all easily available papers irrespective of their publication status, focusing on the combination mechanisms rat…
Massachusetts Institute of Technology（麻省理工学院）；Higher Institute for Applied Sciences and Technology（应用科学与技术高等学院）
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently each state-action pair was visited while taking into consideration state dynamics that play a crucial role in determining the trajectories produced by the policy. The agent is encouraged to change its behavior consistently towards less-visited state-action pairs while attaining good performance by maximizing the expected discounted sum of rewards, resulting i…
Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm, called Shared Experience Actor-Critic (SEAC), applies experience sharing in an actor-critic framework. We evaluate SEAC in a collection of sparse-reward multi-agent environments and find that it consistently outperforms two baselines and two state-of-the-art algorithms by learning in fewer steps and converging to higher returns. In some harder environments, …
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…
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究院）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究院）
Intelligent assistants that follow commands or answer simple questions, such as Siri and Google search, are among the most economically important applications of AI. Future conversational AI assistants promise even greater capabilities and a better user experience through a deeper understanding of the domain, the user, or the user's purposes. But what domain and what methods are best suited to researching and realizing this promise? In this article we argue for the domain of voice document editing and for the methods of model-based reinforcement learning. The primary advantages of voice docume…
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）
Harvard-MIT Health Sciences and Technology（哈佛-麻省理工学院健康科学与技术）；Massachusetts Institute of Technology (MIT)（麻省理工学院）；Massachusetts General Hospital（麻省总医院）；Columbia University（哥伦比亚大学）
Opioids are the preferred medications for the treatment of pain in the intensive care unit. While undertreatment leads to unrelieved pain and poor clinical outcomes, excessive use of opioids puts patients at risk of experiencing multiple adverse effects. In this work, we present a sequential decision making framework for opioid dosing based on deep reinforcement learning. It provides real-time clinically interpretable dosing recommendations, personalized according to each patient's evolving pain and physiological condition. We focus on morphine, one of the most commonly prescribed opioids. To …
We address the problem of safe reinforcement learning from pixel observations. Inherent challenges in such settings are (1) a trade-off between reward optimization and adhering to safety constraints, (2) partial observability, and (3) high-dimensional observations. We formalize the problem in a constrained, partially observable Markov decision process framework, where an agent obtains distinct reward and safety signals. To address the curse of dimensionality, we employ a novel safety critic using the stochastic latent actor-critic (SLAC) approach. The latent variable model predicts rewards and…
