The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment. In an increasing number of applications, data-driven and learning-based approaches, such as deep reinforcement learning, have proven effective at designing control policies. For most tasks, the only way to evaluate a physical design with respect to such control policies is empirical--i.e., by picking a design and training a control policy for it. Since training these policies is time-consuming, it is computationally infeasible to train separate policies for all possible designs as a means to identify the best one. In this work, we address this limitation by introducing a method that performs simultaneous joint optimization of the physical design and control network. Our approach maintains a distribution over designs and uses reinforcement learning to optimize a control policy to maximize expected reward over the design distribution. We give the controller access to design parameters to allow it to tailor its policy to each design in the distribution. Throughout training, we shift the distribution towards higher-performing designs, eventually converging to a design and control policy that are jointly optimal. We evaluate our approach in the context of legged locomotion, and demonstrate that it discovers novel designs and walking gaits, outperforming baselines in both performance and efficiency.
We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior. Our approach uses a variational autoencoder to train a latent space that jointly encodes information about the observations and outcome variables pertaining to an agent's behavior. Counterfactuals are generated using traversals in this latent space, via gradient-driven updates as well as latent interpolations against cases drawn from a pool of examples. These include updates to raise the likelihood …
MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning
JetBrains Research（JetBrains研究院）；National Research University Higher School of Economics（国立研究型大学高等经济学院）；L3S Research Center（L3S研究中心）；Leibniz University Hannover（汉诺威莱布尼茨大学）
While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state representations and the latest work has explored embedding techniques for actions, both with the aim of achieving better generalization and applicability. However, these approaches consider only states or actions, ignoring the interaction between them when generating embedded representations. In this work, we establish the theoretical foundations for the valid…
Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents. However, such sharing may lead agents to behave similarly and limit their coordination capacity. In this paper, we aim to introduce diversity in both optimization and representation of shared multi-agent reinforcement learning. Specifically, we propose an information-theoretical regularization to maximize the mutual information between agents' identities and their trajectories, encouraging extensive exploration and d…
Within the framework of Multi-Agent Reinforcement Learning, Social Learning is a new class of algorithms that enables agents to reshape the reward function of other agents with the goal of promoting cooperation and achieving higher global rewards in mixed-motive games. However, this new modification allows agents unprecedented access to each other's learning process, which can drastically increase the risk of manipulation when an agent does not realize it is being deceived into adopting policies which are not actually in its own best interest. This research review introduces the problem statem…
Alexa AI, Amazon Inc（亚马逊公司Alexa人工智能部门）；University of Southern California（南加州大学）
We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich multi-room home environment. We provide an integrated learning framework, multimodal implementations of state-of-the-art multi-agent reinforcement learning techniques, and a consistent evaluation protocol. Our experiments investigate the impact of different modalities on multi-agent learning performance. We also introduce a simple message passing me…
Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）
Deep Reinforcement Learning (Deep RL) has been in the spotlight for the past few years, due to its remarkable abilities to solve problems which were considered to be practically unsolvable using traditional Machine Learning methods. However, even state-of-the-art Deep RL algorithms have various weaknesses that prevent them from being used extensively within industry applications, with one such major weakness being their sample-inefficiency. In an effort to patch these issues, we integrated a meta-learning technique in order to shift the objective of learning to solve a task into the objective …
Multi-agent reinforcement learning (MARL) has achieved great progress in cooperative tasks in recent years. However, in the local reward scheme, where only local rewards for each agent are given without global rewards shared by all the agents, traditional MARL algorithms lack sufficient consideration of agents' mutual influence. In cooperative tasks, agents' mutual influence is especially important since agents are supposed to coordinate to achieve better performance. In this paper, we propose a novel algorithm Mutual-Help-based MARL (MH-MARL) to instruct agents to help each other in order to …
Sparse and delayed rewards pose a challenge to single agent reinforcement learning. This challenge is amplified in multi-agent reinforcement learning (MARL) where credit assignment of these rewards needs to happen not only across time, but also across agents. We propose Agent-Time Attention (ATA), a neural network model with auxiliary losses for redistributing sparse and delayed rewards in collaborative MARL. We provide a simple example that demonstrates how providing agents with their own local redistributed rewards and shared global redistributed rewards motivate different policies. We exten…
We present Godot Reinforcement Learning (RL) Agents, an open-source interface for developing environments and agents in the Godot Game Engine. The Godot RL Agents interface allows the design, creation and learning of agent behaviors in challenging 2D and 3D environments with various on-policy and off-policy Deep RL algorithms. We provide a standard Gym interface, with wrappers for learning in the Ray RLlib and Stable Baselines RL frameworks. This allows users access to over 20 state of the art on-policy, off-policy and multi-agent RL algorithms. The framework is a versatile tool that allows re…
MASQ: Multi-Agent Reinforcement Learning for Single Quadruped Robot Locomotion
Harbin Institute of Technology Shenzhen（哈尔滨工业大学（深圳））；School of Mechanical Engineering and Automation（机械工程与自动化学院）；Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics（广东省智能变胞机构与自适应机器人重点实验室）
We examine the problem of transmission control, i.e., when to transmit, in distributed wireless communications networks through the lens of multi-agent reinforcement learning. Most other works using reinforcement learning to control or schedule transmissions use some centralized control mechanism, whereas our approach is fully distributed. Each transmitter node is an independent reinforcement learning agent and does not have direct knowledge of the actions taken by other agents. We consider the case where only a subset of agents can successfully transmit at a time, so each agent must learn to …
Traditionally, the performance of multi-agent deep reinforcement learning algorithms are demonstrated and validated in gaming environments where we often have a fixed number of agents. In many industrial applications, the number of available agents can change at any given day and even when the number of agents is known ahead of time, it is common for an agent to break during the operation and become unavailable for a period of time. In this paper, we propose a new deep reinforcement learning algorithm for multi-agent collaborative tasks with a variable number of agents. We demonstrate the appl…
University of Virginia（弗吉尼亚大学）；Bar-Ilan University（巴伊兰大学）
Advances in multi-agent reinforcement learning (MARL) enable sequential decision making for a range of exciting multi-agent applications such as cooperative AI and autonomous driving. Explaining agent decisions is crucial for improving system transparency, increasing user satisfaction, and facilitating human-agent collaboration. However, existing works on explainable reinforcement learning mostly focus on the single-agent setting and are not suitable for addressing challenges posed by multi-agent environments. We present novel methods to generate two types of policy explanations for MARL: (i) …
Models and games are simplified representations of the world. There are many different kinds of models, all differing in complexity and which aspect of the world they allow us to further our understanding of. In this paper we focus on a specific instance of agent-based models, which uses reinforcement learning (RL) to train the agent how to act in its environment. Reinforcement learning agents are usually also Markov processes, which is another type of model that can be used. We test this reinforcement learning agent in a Colonel Blotto environment1, and measure its performance against Random …
In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are triggers native to the data distributions the model will be trained on and deployed in. We outline a simple procedure for embedding these, and other, triggers in deep reinforcement learning agents following a multi-task learning paradigm, and demonstrate in three common reinforcement learning environments. We believe that this work has important implications for the security of deep learning models.
University of Science and Technology of China（中国科学技术大学）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）
Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes will destroy the cooperation among agents, leading to performance degradation. In this work, we present a formal formulation of a cooperative multi-agent reinforcement lea…
A Visual Communication Map for Multi-Agent Deep Reinforcement Learning
Institute for Intelligent Systems Research and Innovation, Deakin University（迪肯大学智能系统研究与创新研究所）；School of Information Technology, Deakin University（迪肯大学信息技术学院）
Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning
Tata Consultancy Services（塔塔咨询服务公司）；Birla Institute of Technology and Science, Goa（果阿贝拉理工学院）；University of Edinburgh（爱丁堡大学）；University of Manchester（曼彻斯特大学）；Indian Institute of Technology, Bombay（印度理工学院孟买分校）
Multi-agent reinforcement learning experiments and open-source training environments are typically limited in scale, supporting tens or sometimes up to hundreds of interacting agents. In this paper we demonstrate the use of Vogue, a high performance agent based model (ABM) framework. Vogue serves as a multi-agent training environment, supporting thousands to tens of thousands of interacting agents while maintaining high training throughput by running both the environment and reinforcement learning (RL) agents on the GPU. High performance multi-agent environments at this scale have the potentia…
College of Engineering, Peking University（北京大学工学院）；State Key Laboratory of Turbulence and Complex Systems（湍流与复杂系统国家重点实验室）；The Hong Kong University of Science and Technology（香港科技大学）
A reinforcement learning environment with adversary agents is proposed in this work for pursuit-evasion game in the presence of fog of war, which is of both scientific significance and practical importance in aerospace applications. One of the most popular learning environments, StarCraft, is adopted here and the associated mini-games are analyzed to identify the current limitation for training adversary agents. The key contribution includes the analysis of the potential performance of an agent by incorporating control and differential game theory into the specific reinforcement learning envir…
Recently, deep reinforcement learning (RL) algorithms have made great progress in multi-agent domain. However, due to characteristics of RL, training for complex tasks would be resource-intensive and time-consuming. To meet this challenge, mutual learning strategy between homogeneous agents is essential, which is under-explored in previous studies, because most existing methods do not consider to use the knowledge of agent models. In this paper, we present an adaptation method of the majority of multi-agent reinforcement learning (MARL) algorithms called KnowSR which takes advantage of the dif…
We study the benefits of reinforcement learning (RL) environments based on agent-based models (ABM). While ABMs are known to offer microfoundational simulations at the cost of computational complexity, we empirically show in this work that their non-deterministic dynamics can improve the generalization of RL agents. To this end, we examine the control of an epidemic SIR environments based on either differential equations or ABMs. Numerical simulations demonstrate that the intrinsic noise in the ABM-based dynamics of the SIR model not only improve the average reward but also allow the RL agent …
We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning. We define two agents, a goal conditioned agent (GC-agent) and a supervised agent (S-agent). Given a user-input initial state, the GC-agent learns to reconstruct the training set. In this context, elements in the training set are the goals. During training, the S-agent learns to imitate the GC-agent while remaining agnostic of the goals. At inference we generate new samples with the S-agent. Following a similar route as in variational auto-encoders, we derive an upper bound on …
Federation University（联邦大学）；Deakin University（迪肯大学）；Universidad Central de Chile（智利中央大学）；University of Alberta（阿尔伯塔大学）；Action Research Associates（行动研究协会）
A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning pro…
McGill University（麦吉尔大学）；Mila；Université de Montréal（蒙特利尔大学）；DeepMind
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with several sets of customized environments featuring different challenges. We consistently observe that the design allows the planning agents to generalize their learned task-solving abilities in compatible unseen environments by at…
