The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However, one critical feature in MARL that is often neglected is that the interactions between agents are quite sparse. Without exploiting this sparsity structure, existing works aggregate information from all of the agents and thus have a high sample complexity. To address this issue, we propose an adaptive sparse attention mechanism by generalizing a sparsity-inducing activation function. Then a sparse communication graph in MARL is learned by graph neural networks based on this new attention mechanism. Through this sparsity structure, the agents can communicate in an effective as well as efficient way via only selectively attending to agents that matter the most and thus the scale of the MARL problem is reduced with little optimality compromised. Comparative results show that our algorithm can learn an interpretable sparse structure and outperforms previous works by a significant margin on applications involving a large-scale multiagent system.
University of Chinese Academy of Sciences（中国科学院大学）；Electronics Technology Group Corporation Information Science Academy of China（中国电子科技集团公司信息科学研究院）
Multiagent reinforcement learning (MARL) can solve complex cooperative tasks. However, the efficiency of existing MARL methods relies heavily on well-defined reward functions. Multiagent tasks with sparse reward feedback are especially challenging not only because of the credit distribution problem, but also due to the low probability of obtaining positive reward feedback. In this paper, we design a graph network called Cooperation Graph (CG). The Cooperation Graph is the combination of two simple bipartite graphs, namely, the Agent Clustering subgraph (ACG) and the Cluster Designating subgrap…
Tianjin University（天津大学）；Netease Fuxi AI Lab（网易伏羲人工智能实验室）；Nanjing University（南京大学）
Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long trajectories. In this paper, we study hierarchical deep MARL in cooperative multiagent problems with sparse and delayed reward. With temporal abstraction, we decompose the problem into a hierarchy of different time scales and investigate how agents can learn high-level coordination based on the independent skills learned at the low level. Three hierarchical deep MARL …
Intel Labs（英特尔实验室）；University of California, Irvine（加州大学欧文分校）；Oregon State University（俄勒冈州立大学）
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based reward is often difficult due to its sparsity. Furthermore, relying solely on the agent-specific reward is sub-optimal because it usually does not capture the team coordination objective. A common approach is to use reward shaping to construct a proxy reward by combining the individual rewards. However, this requires manual tuning for each environment. We intro…
Tianjin University（天津大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Northwestern Polytechnical University（西北工业大学）
Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant successes across a wide range of domains, including game AI, autonomous vehicles, robotics, and so on. However, DRL and deep MARL agents are widely known to be sample inefficient that millions of interactions are usually needed even for relatively simple problem settings, thus preventing the wide application and deployment in real-industry scenarios. One bottleneck challenge behind is the well-known exploration problem, i.e., how efficiently exploring the environment and collecting in…
The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade
Massachusetts Institute of Technology（麻省理工学院）；Stanford University（斯坦福大学）；New York University（纽约大学）；AICrowd；NetEase Games AI Lab（网易游戏人工智能实验室）；Bilibili（哔哩哔哩）；Chengdu Goldwin Electronics Technology Co., Ltd（成都金盘电子科技有限公司）；Advanced Network Technology Laboratory, Beijing University of Posts and Telecommunications（北京邮电大学先进网络技术实验室）；The Hong Kong Chinese University（香港中文大学）；The Hong Kong City University（香港城市大学）
Massachusetts Institute of Technology（麻省理工学院）；Horizon Robotics（地平线机器人）
In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals. To address the issues reinforcement learning algorithms face when task rewards are sparse, this paper proposes an intrinsic motivation approach that can be easily integrated into any standard reinforcement learning algorithm and can allow robotic manipulators to learn useful manipulation skills with only sparse extrinsic rewards. Through integrating and balancing empowerment and curios…
Rochester Institute of Technology（罗切斯特理工学院）；The University of South Florida（南佛罗里达大学）
In this article, we propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC), designing an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards, embodying the principles of planning-as-inference. Concretely, we craft an adaptive agent system, which we call active predictive coding (ActPC), that balances an internally-generated epistemic signal (meant to encourage intelligent exploration) with an internally-generated instrumen…
In this paper, we present a novel Heavy-Tailed Stochastic Policy Gradient (HT-PSG) algorithm to deal with the challenges of sparse rewards in continuous control problems. Sparse reward is common in continuous control robotics tasks such as manipulation and navigation, and makes the learning problem hard due to non-trivial estimation of value functions over the state space. This demands either reward shaping or expert demonstrations for the sparse reward environment. However, obtaining high-quality demonstrations is quite expensive and sometimes even impossible. We propose a heavy-tailed policy…
Beihang University（北京航空航天大学）；Nanjing Research Institute of Electronics Technology（南京电子技术研究所）
The application of reinforcement learning (RL) in robotic control is still limited in the environments with sparse and delayed rewards. In this paper, we propose a practical self-imitation learning method named Self-Imitation Learning with Constant Reward (SILCR). Instead of requiring hand-defined immediate rewards from environments, our method assigns the immediate rewards at each timestep with constant values according to their final episodic rewards. In this way, even if the dense rewards from environments are unavailable, every action taken by the agents would be guided properly. We demons…
The multiagent-based participatory simulation features prominently in urban planning as the acquired model is considered as the hybrid system of the domain and the local knowledge. However, the key problem of generating realistic agents for particular social phenomena invariably remains. The existing models have attempted to dictate the factors involving human behavior, which appeared to be intractable. In this paper, Inverse Reinforcement Learning (IRL) is introduced to address this problem. IRL is developed for computational modeling of human behavior and has achieved great successes in robo…
California Institute of Technology（加州理工学院）；University of California, Berkeley（加州大学伯克利分校）
Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging. We address these issues with a new model-based reinforcement learning algorithm, Safety Augmented Value Estimation from Demonstrations (SAVED), which uses supervision that only identifies task completion and a modest set of suboptimal demonstrations to constrain exploration and learn efficiently while handling complex constraints. We then compare…
University College Dublin（都柏林大学学院）；Dublin City University（都柏林城市大学）；Insight SFI Research Centre for Data Analytics（Insight SFI数据分析研究中心）；Harvard University（哈佛大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；KTH Stockholm（斯德哥尔摩皇家理工学院）
This paper describes a deep reinforcement learning (DRL) approach that won Phase 1 of the Real Robot Challenge (RRC) 2021, and then extends this method to a more difficult manipulation task. The RRC consisted of using a TriFinger robot to manipulate a cube along a specified positional trajectory, but with no requirement for the cube to have any specific orientation. We used a relatively simple reward function, a combination of goal-based sparse reward and distance reward, in conjunction with Hindsight Experience Replay (HER) to guide the learning of the DRL agent (Deep Deterministic Policy Gra…
This paper considers a multiagent, connected, robotic fleet where the primary functionality of the agents is sensing. A distributed multi-sensor control strategy maximizes the value of the collective sensing capability of the fleet, using an information-driven approach. Each agent individually performs sensor processing (Kalman Filtering and Joint Probabilistic Data Association) to identify trajectories (and associated distributions). Using communications with its neighbors the agents enhance the prediction of the trajectories using a Consensus of Information approach that iteratively calculat…
Norwegian University of Science and Technology (NTNU)（挪威科技大学）；Centre for Autonomous Marine Operations and Systems (AMOS)（自主海洋作业与系统中心）
This paper deals with robotic lever control using Explainable Deep Reinforcement Learning. First, we train a policy by using the Deep Deterministic Policy Gradient algorithm and the Hindsight Experience Replay technique, where the goal is to control a robotic manipulator to manipulate a lever. This enables us both to use continuous states and actions and to learn with sparse rewards. Being able to learn from sparse rewards is especially desirable for Deep Reinforcement Learning because designing a reward function for complex tasks such as this is challenging. We first train in the PyBullet sim…
Although Deep Reinforcement Learning (DRL) has been popular in many disciplines including robotics, state-of-the-art DRL algorithms still struggle to learn long-horizon, multi-step and sparse reward tasks, such as stacking several blocks given only a task-completion reward signal. To improve learning efficiency for such tasks, this paper proposes a DRL exploration technique, termed A^2, which integrates two components inspired by human experiences: Abstract demonstrations and Adaptive exploration. A^2 starts by decomposing a complex task into subtasks, and then provides the correct orders of s…
The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existing robotics hardware. The tasks include pushing, sliding and pick & place with a Fetch robotic arm as well as in-hand object manipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards and follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent is told what to do using an additional input. The second part of the paper presents a set of concrete research ideas for improving RL a…
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only when the task has been successfully completed, can lead to better policies. However, state-action space exploration is more difficult in this case. Recent RL approaches to learning with sparse rewards have leveraged high-quality human demonstrations for the task, but these can be costly, time consuming or even impossible to obtain. In this paper, we propose …
Technical University of Darmstadt（达姆施塔特工业大学）；Mitsubishi Electric Research Laboratories（三菱电机研究实验室）
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years. One of the key challenges in manipulation is the exploration of the dynamics of the environment when there is continuous contact between the objects being manipulated. This paper proposes a model-based active exploration approach that enables efficient learning in sparse-reward robotic manipulation tasks. The proposed method estimates an information gain objective using an ensemble of probabilistic models and deploys model predictive control (MPC) to plan act…
Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation
U.S. Army Research Laboratory（美国陆军研究实验室）；JP Morgan AI Research（摩根大通人工智能研究院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Central Florida（中佛罗里达大学）
This work re-implements the OpenAI Gym multi-goal robotic manipulation environment, originally based on the commercial Mujoco engine, onto the open-source Pybullet engine. By comparing the performances of the Hindsight Experience Replay-aided Deep Deterministic Policy Gradient agent on both environments, we demonstrate our successful re-implementation of the original environment. Besides, we provide users with new APIs to access a joint control mode, image observations and goals with customisable camera and a built-in on-hand camera. We further design a set of multi-step, multi-goal, long-hori…
Vision-Language-Action Jump-Starting for Reinforcement Learning Robotic Agents
University of Applied Science and Arts of Southern Switzerland, Department of Innovative Technologies（瑞士南方应用科学与艺术大学创新技术系）；Università della Svizzera Italiana, Faculty of Informatics, Lugano, Switzerland（瑞士意大利大学信息学院，卢加诺，瑞士）
Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Université de Lorraine（洛林大学）
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effective exploration strategy to deal with sparse or misleading reward scenarios: if they do not experience any state with a positive reward during the initial random exploration, it is very unlikely to solve the problem. Here, we propose a novel model-based policy search algorithm, …
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL. The key idea behind our method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL. Our experiments in several chall…
While recent progress in deep reinforcement learning has enabled robots to learn complex behaviors, tasks with long horizons and sparse rewards remain an ongoing challenge. In this work, we propose an effective reward shaping method through predictive coding to tackle sparse reward problems. By learning predictive representations offline and using these representations for reward shaping, we gain access to reward signals that understand the structure and dynamics of the environment. In particular, our method achieves better learning by providing reward signals that 1) understand environment dy…
Continuum robotic manipulators are increasingly adopted in minimal invasive surgery. However, their nonlinear behavior is challenging to model accurately, especially when subject to external interaction, potentially leading to poor control performance. In this letter, we investigate the feasibility of adopting a model-free multiagent reinforcement learning (RL), namely multiagent deep Q network (MADQN), to control a 2-degree of freedom (DoF) cable-driven continuum surgical manipulator. The control of the robot is formulated as a one-DoF, one agent problem in the MADQN framework to improve the …
Tsinghua University（清华大学）；University of California, Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）；Shanghai Qi Zhi Institute（上海期智研究院）
It has been a recent trend to leverage the power of supervised learning (SL) towards more effective reinforcement learning (RL) methods. We propose a novel phasic approach by alternating online RL and offline SL for tackling sparse-reward goal-conditioned problems. In the online phase, we perform RL training and collect rollout data while in the offline phase, we perform SL on those successful trajectories from the dataset. To further improve sample efficiency, we adopt additional techniques in the online phase including task reduction to generate more feasible trajectories and a value-differe…
Universitat Pompeu Fabra（庞培法布拉大学）；ICREA, Institució Catalana de Recerca i Estudis Avançats（加泰罗尼亚高等研究院）
A first step to reach Theory of Mind (ToM) abilities (attribution of beliefs to others) in synthetic agents through sensorimotor interactions, would be to tag sensory data with agent typology and action intentions: autonomous agent X moved an object under the box. We propose a dual arm robotic setup in which ToM could be probed. We then discuss what measures can be extracted from sensorimotor interaction data (based on a correlation analysis) in the proposed setup that allow to distinguish self than other and other/inanimate from other/active with intentions. We finally discuss what elements a…
Dyson Robotics Lab（戴森机器人实验室）；Imperial College London（帝国理工学院）
We present a coarse-to-fine discretisation method that enables the use of discrete reinforcement learning approaches in place of unstable and data-inefficient actor-critic methods in continuous robotics domains. This approach builds on the recently released ARM algorithm, which replaces the continuous next-best pose agent with a discrete one, with coarse-to-fine Q-attention. Given a voxelised scene, coarse-to-fine Q-attention learns what part of the scene to 'zoom' into. When this 'zooming' behaviour is applied iteratively, it results in a near-lossless discretisation of the translation space,…
Forschungszentrum Jülich（于利希研究中心）；RWTH Aachen University（亚琛工业大学）；Technische Universität Berlin（柏林工业大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Korea University（高丽大学）
The ability to handle single molecules as effectively as macroscopic building-blocks would enable the construction of complex supramolecular structures inaccessible to self-assembly. The fundamental challenges obstructing this goal are the uncontrolled variability and poor observability of atomic-scale conformations. Here, we present a strategy to work around both obstacles, and demonstrate autonomous robotic nanofabrication by manipulating single molecules. Our approach employs reinforcement learning (RL), which finds solution strategies even in the face of large uncertainty and sparse feedba…
Delft University of Technology（代尔夫特理工大学）；Massachusetts Institute of Technology（麻省理工学院）
Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directly observable and the environment conditions are continuously changing. Local trajectory optimization methods, such as model predictive control (MPC), can deal with those changes but require global guidance, which is not trivial to obtain in crowded scenarios. This paper proposes to learn, via deep Reinforcement Learning (RL), an interaction-aware policy that provides long-term guidance to the local planner. In particular, in simulations with …
MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models
School of Intelligent Science and Technology, Nanjing University, China（南京大学智能科学与技术学院）；National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China（南京大学新型软件技术国家实验室，人工智能学院）；School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院）；MACS Lab, University of Washington（华盛顿大学MACS实验室）
Hamburg University of Technology（汉堡工业大学）；University of Hamburg（汉堡大学）
This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding of language in sensory data and actions. We address these issues with three contributions. We first present a mechanism for hindsight instruction replay utilizing expert feedback. Second, we propose a seq2seq model to generate linguistic hindsight instructions. Finally, we present a novel class of language-focused learning tasks. We show that hindsight instr…
Despite the potential of reinforcement learning (RL) for building general-purpose robotic systems, training RL agents to solve robotics tasks still remains challenging due to the difficulty of exploration in purely continuous action spaces. Addressing this problem is an active area of research with the majority of focus on improving RL methods via better optimization or more efficient exploration. An alternate but important component to consider improving is the interface of the RL algorithm with the robot. In this work, we manually specify a library of robot action primitives (RAPS), paramete…
University of Hamburg（汉堡大学）；Knowledge Technology, Department of Informatics（知识技术与信息学系）
Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this direction inspired by human mental simulation of motor behavior. We propose a learning-adaptive imagination approach which, unlike previous approaches, takes into account the reliability of the learned dynamics model used for imagining the future. Our approach learns an ensemble of disjoint local dynamics models in latent space and derives an intrinsic reward…
In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencoder which is trained to reconstruct the visual input, while the centre-most hidden representation is also optimized to estimate the state value. Separately, an ensemble of predictive world models generates, based on its learning progress, an intrinsic reward signal which is combined with the extrinsic…
Reinforcement learning is an appropriate and successful method to robustly perform low-level robot control under noisy conditions. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration of both approaches is that action planning is based on discrete high-level action- and state spaces, whereas reinforcement learning is usually driven by a continuous reward function. However, recent advances in reinforcement learning, specifically, universal value function approx…
Warwick Manufacturing Group（华威制造集团）；University of Warwick（华威大学）
Learning with sparse rewards remains a significant challenge in reinforcement learning (RL), especially when the aim is to train a policy capable of achieving multiple different goals. To date, the most successful approaches for dealing with multi-goal, sparse reward environments have been model-free RL algorithms. In this work we propose PlanGAN, a model-based algorithm specifically designed for solving multi-goal tasks in environments with sparse rewards. Our method builds on the fact that any trajectory of experience collected by an agent contains useful information about how to achieve the…
Dyson Robotics Lab, Imperial College London（戴森机器人实验室，帝国理工学院）
Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks. This is partly due to the fact that reinforcement learning algorithms are notoriously difficult and time consuming to train, which is exacerbated when training from images rather than full-state inputs. As humans perform manipulation tasks, our eyes closely monitor every step of the process with our gaze focusing sequentially on the objects being manipulated. With this in mind, we present our Attention-driven Robotic Manipulation (A…
Sparse rewards present a difficult problem in reinforcement learning and may be inevitable in certain domains with complex dynamics such as real-world robotics. Hindsight Experience Replay (HER) is a recent replay memory development that allows agents to learn in sparse settings by altering memories to show them as successful even though they may not be. While, empirically, HER has shown some success, it does not provide guarantees around the makeup of samples drawn from an agent's replay memory. This may result in minibatches that contain only memories with zero-valued rewards or agents learn…
ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, and D'Kitty is a four-legged robot that facilitates learning agile legged locomotion tasks. These low-cost, modular robots are easy to maintain and are robust enough to sustain on-hardware reinforcement learning from scratch with over 14000 training hours registered on them to da…
OpenAI；University of California, Berkeley（加州大学伯克利分校）
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous con…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Robert Bosch Center for Data Science and AI (RBCDSAI)（罗伯特·博世数据科学与人工智能中心（RBCDSAI））
Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to easier goals first, and then gradually increasing their difficulty. This paper takes a similar direction and proposes a dual curriculum scheme for solving robotic manipulation tasks with sparse rewards, called MaMiC. It includes a macro curriculum scheme which divides the task i…
