Multi-agent systems have a wide range of applications in cooperative and competitive tasks. As the number of agents increases, nonstationarity gets more serious in multi-agent reinforcement learning (MARL), which brings great difficulties to the learning process. Besides, current mainstream algorithms configure each agent an independent network,so that the memory usage increases linearly with the number of agents which greatly slows down the interaction with the environment. Inspired by Generative Adversarial Networks (GAN), this paper proposes an iterative update method (IU) to stabilize the nonstationary environment. Further, we add first-person perspective and represent all agents by only one network which can change agents' policies from sequential compute to batch compute. Similar to continual lifelong learning, we realize the iterative update method in this unified representative network (IUUR). In this method, iterative update can greatly alleviate the nonstationarity of the environment, unified representation can speed up the interaction with environment and avoid the linear growth of memory usage. Besides, this method does not bother decentralized execution and distributed deployment. Experiments show that compared with MADDPG, our algorithm achieves state-of-the-art performance and saves wall-clock time by a large margin especially with more agents.
MIT（麻省理工学院）；Harvard Medical School（哈佛医学院）；Harvard Pilgrim Healthcare Institute（哈佛朝圣者医疗保健研究所）
Reinforcement learning (RL) has the potential to significantly improve clinical decision making. However, treatment policies learned via RL from observational data are sensitive to subtle choices in study design. We highlight a simple approach, trajectory inspection, to bring clinicians into an iterative design process for model-based RL studies. We identify where the model recommends unexpectedly aggressive treatments or expects surprisingly positive outcomes from its recommendations. Then, we examine clinical trajectories simulated with the learned model and policy alongside the actual hospi…
Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather than providing the agent with an externally provided curriculum of progressively more difficult tasks, the agent solves a single task utilizing a decreasingly constrained policy space. The algorithm we propose first learns to categorize features into positive and negative before gradually learning a more refined policy. Experimental results in Tetris demonstr…
University of Edinburgh（爱丁堡大学）；University of Sussex（苏塞克斯大学）
There are several ways to categorise reinforcement learning (RL) algorithms, such as either model-based or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as these help provide a unified perspective on disparate techniques and can contextualise and guide the development of new algorithms. In this paper, we utilise the control as inference framework to outline a novel classification scheme based on amortised and iterative inference. We demonstrate that a wide range of algorithms can be classified in this manner provid…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the non-expansion property, and its direct use may fail to converge even in value iteration. In this paper, we propose to update the value function with dynamic Boltzmann softmax (DBS) operator, which has good convergence property in the setting of planning and learning. Experimental results on GridWorld show that the DBS operator enables better estimation of the value function, whi…
University of Oulu（奥卢大学）；Linköping University（林雪平大学）
We consider an IoT sensing network with multiple users, multiple energy harvesting sensors, and a wireless edge node acting as a gateway between the users and sensors. The users request for updates about the value of physical processes, each of which is measured by one sensor. The edge node has a cache storage that stores the most recently received measurements from each sensor. Upon receiving a request, the edge node can either command the corresponding sensor to send a status update, or use the data in the cache. We aim to find the best action of the edge node to minimize the average long-te…
Sony AI（索尼AI）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Designing reinforcement learning (RL) agents is typically a difficult process that requires numerous design iterations. Learning can fail for a multitude of reasons, and standard RL methods provide too few tools to provide insight into the exact cause. In this paper, we show how to integrate value decomposition into a broad class of actor-critic algorithms and use it to assist in the iterative agent-design process. Value decomposition separates a reward function into distinct components and learns value estimates for each. These value estimates provide insight into an agent's learning and deci…
University of Cambridge（剑桥大学）；Google DeepMind（谷歌DeepMind）；UC Berkeley（加州大学伯克利分校）
Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinf…
$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning
Department of Computer Science, TU Darmstadt（图恩-达姆施塔特技术大学计算机科学系）；Hessian Center for Artificial Intelligence (Hessian.ai)（黑森人工智能中心）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Center for Cognitive Science, TU Darmstadt（图恩-达姆施塔特技术大学认知科学中心）；Center for Artificial Intelligence and Data Science, University of Würzburg（弗赖堡大学人工智能与数据科学中心）
Peking University（北京大学）；Zhejiang University（浙江大学）；Tsinghua University（清华大学）；Netease Games AI Lab（网易游戏人工智能实验室）
Safe reinforcement learning (RL) is still very challenging since it requires the agent to consider both return maximization and safe exploration. In this paper, we propose CUP, a Conservative Update Policy algorithm with a theoretical safety guarantee. We derive the CUP based on the new proposed performance bounds and surrogate functions. Although using bounds as surrogate functions to design safe RL algorithms have appeared in some existing works, we develop them at least three aspects: (i) We provide a rigorous theoretical analysis to extend the surrogate functions to generalized advantage e…
The Technion - Israel Institute of Technology（以色列理工学院）；UC Berkeley（加州大学伯克利分校）
Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or policy. Batch reinforcement learning methods with linear representations, on the other hand, are more stable and require less hyper parameter tuning. Yet, substantial feature engineering is necessary to achieve good results. In this work we propose a hybrid approach -- the Least Squ…
IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning
Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）；School of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；Kuaishou Technology（快手科技）；Shenzhen Institute of Advanced Integration Technology, Shenzhen（深圳先进集成技术研究院）
FiveAI（FiveAI公司）；The University of Edinburgh（爱丁堡大学）
We propose a lifelong learning architecture, the Neural Computer Agent (NCA), where a Reinforcement Learning agent is paired with a predictive model of the environment learned by a Differentiable Neural Computer (DNC). The agent and DNC model are trained in conjunction iteratively. The agent improves its policy in simulations generated by the DNC model and rolls out the policy to the live environment, collecting experiences in new portions or tasks of the environment for further learning. Experiments in two synthetic environments show that DNC models can continually learn from pixels alone to …
We propose Episodic Backward Update (EBU) - a novel deep reinforcement learning algorithm with a direct value propagation. In contrast to the conventional use of the experience replay with uniform random sampling, our agent samples a whole episode and successively propagates the value of a state to its previous states. Our computationally efficient recursive algorithm allows sparse and delayed rewards to propagate directly through all transitions of the sampled episode. We theoretically prove the convergence of the EBU method and experimentally demonstrate its performance in both deterministic…
Several low-bandwidth distributable black-box optimization algorithms in the family of finite differences such as Evolution Strategies have recently been shown to perform nearly as well as tailored Reinforcement Learning methods in some Reinforcement Learning domains. One shortcoming of these black-box methods is that they must collect information about the structure of the return function at every update, and can often employ only information drawn from a distribution centered around the current parameters. As a result, when these algorithms are distributed across many machines, a significant…
University of Hong Kong（香港大学）；University of Alberta（阿尔伯塔大学）
Using neural networks in the reinforcement learning (RL) framework has achieved notable successes. Yet, neural networks tend to forget what they learned in the past, especially when they learn online and fully incrementally, a setting in which the weights are updated after each sample is received and the sample is then discarded. Under this setting, an update can lead to overly global generalization by changing too many weights. The global generalization interferes with what was previously learned and deteriorates performance, a phenomenon known as catastrophic interference. Many previous work…
Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
Department of Computer Science, University of Toronto（多伦多大学计算机科学系）；Department of Statistics（统计学系）；Data Science, Northwestern University（数据科学，西北大学）；Bridgewater AIA Labs（布里奇沃特AIA实验室）
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
This paper proposes a new robust update rule of target network for deep reinforcement learning (DRL), to replace the conventional update rule, given as an exponential moving average. The target network is for smoothly generating the reference signals for a main network in DRL, thereby reducing learning variance. The problem with its conventional update rule is the fact that all the parameters are smoothly copied with the same speed from the main network, even when some of them are trying to update toward the wrong directions. This behavior increases the risk of generating the wrong reference s…
Texas A&M University（得克萨斯农工大学）；US Army Research Laboratory（美国陆军研究实验室）；Columbia University（哥伦比亚大学）
This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning from Demonstrations, for example behavior cloning, can lead to proficient policies given limited data. However, it is currently unclear how to efficiently update that policy using reinforcement learning as these approaches are inherently optimizing different objective functions. Previous works have used loss functions, which combine behavior cloning losses with reinforcement lea…
Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient algorithms, or algorithms that are better adapted to specific environments. Although there have been prior attempts at addressing this significant scientific challenge, it remains an open question whether it is feasible to discover alternatives to fundamental concepts of RL such as value functions and temporal-difference learning. This paper introduces a new …
In Multi-Agent Reinforcement Learning (MA-RL), independent cooperative learners must overcome a number of pathologies to learn optimal joint policies. Addressing one pathology often leaves approaches vulnerable towards others. For instance, hysteretic Q-learning addresses miscoordination while leaving agents vulnerable towards misleading stochastic rewards. Other methods, such as leniency, have proven more robust when dealing with multiple pathologies simultaneously. However, leniency has predominately been studied within the context of strategic form games (bimatrix games) and fully observabl…
Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
University of Minnesota（明尼苏达大学）；Texas A&M University（德克萨斯A&M大学）；University of California, Davis（加利福尼亚大学戴维斯分校）；Amazon（亚马逊）；The Chinese University of Hong Kong（香港中文大学）
Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updates parameters in primal and dual spaces in turn. Existing methods for CMDPs only use on-policy data for dual updates, which results in sample inefficiency and slow convergence. In this paper, we propose a policy search method for CMDPs called Accelerated Primal-Dual Optimization …
Reinforcement learning is a popular machine learning paradigm which can find near optimal solutions to complex problems. Most often, these procedures involve function approximation using neural networks with gradient based updates to optimise weights for the problem being considered. While this common approach generally works well, there are other update mechanisms which are largely unexplored in reinforcement learning. One such mechanism is Extreme Learning Machines. These were initially proposed to drastically improve the training speed of neural networks and have since seen many application…
University of Cambridge（剑桥大学）；DeepMind；Max Planck Institute（马克斯·普朗克研究所）；Uber AI Labs（Uber人工智能实验室）；UC Berkeley（加州大学伯克利分校）
Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to use. This paper examines, both theoretically and empirically, approaches to merging on- and off-policy updates for deep reinforcement learning. Theoretical results show that off-policy updates with a value function estimator can be interpolated with on-policy policy gradient updates whilst still satisfying performance bounds. Our analysis uses control variate…
Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
Technical University of Darmstadt（达姆斯塔特技术大学）；Lund University（隆德大学）；German Research Center for AI (DFKI)（人工智能研究中心（DFKI））；Robotics Institute Germany (RIG)（德国机器人研究所（RIG））；Huawei, Noah’s Ark Lab（华为诺亚实验室）；University College London（伦敦大学学院）
We propose a novel reinforcement learning-based approach for adaptive and iterative feature selection. Given a masked vector of input features, a reinforcement learning agent iteratively selects certain features to be unmasked, and uses them to predict an outcome when it is sufficiently confident. The algorithm makes use of a novel environment setting, corresponding to a non-stationary Markov Decision Process. A key component of our approach is a guesser network, trained to predict the outcome from the selected features and parametrizing the reward function. Applying our method to a national s…
We propose a framework based on distributional reinforcement learning and recent attempts to combine Bayesian parameter updates with deep reinforcement learning. We show that our proposed framework conceptually unifies multiple previous methods in exploration. We also derive a practical algorithm that achieves efficient exploration on challenging control tasks.
We develop a parameterized Primal-Dual $π$ Learning method based on deep neural networks for Markov decision process with large state space and off-policy reinforcement learning. In contrast to the popular Q-learning and actor-critic methods that are based on successive approximations to the nonlinear Bellman equation, our method makes primal-dual updates to the policy and value functions utilizing the fundamental linear Bellman duality. Naive parametrization of the primal-dual $π$ learning method using deep neural networks would encounter two major challenges: (1) each update requires computi…
Graduate School of Science and Technology, Nara Institute of Science and Technology（奈良科学技术大学大学院科学技术研究科）
This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in general infinite-horizon MDPs, we derive an entropy-regularization aware lower bound. Since our bound only requires the expected policy advantage function to be estimated, it is scalable to large-scale (continuous) state-space problems. We propose a novel reinforcement learning algorithm that exploits this lower-bound as a criterion for adjusting the degree of a…
