Related papers: Modular Reinforcement Learning For Cooperative Swa…
This paper presents LEMURS, an algorithm for learning scalable multi-robot control policies from cooperative task demonstrations. We propose a port-Hamiltonian description of the multi-robot system to exploit universal physical constraints…
Building a distributed spatial awareness within a swarm of locally sensing and communicating robots enables new swarm algorithms. We use local observations by robots of each other and Gaussian Belief Propagation message passing combined…
Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the…
Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of…
Modular robots can be reconfigured to create a variety of designs from a small set of components. But constructing a robot's hardware on its own is not enough -- each robot needs a controller. One could create controllers for some designs…
It is of great challenge, though promising, to coordinate collective robots for hunting an evader in a decentralized manner purely in light of local observations. In this paper, this challenge is addressed by a novel hybrid cooperative…
Recent advances in multi-agent reinforcement learning (MARL) are enabling impressive coordination in heterogeneous multi-robot teams. However, existing approaches often overlook the challenge of generalizing learned policies to teams of new…
Multi-robot manipulation tasks involve various control entities that can be separated into dynamically independent parts. A typical example of such real-world tasks is dual-arm manipulation. Learning to naively solve such tasks with…
Collective intelligence and autonomy of robot swarms can be improved by enabling the individual robots to become aware they are the constituent units of a larger whole and what is their role. In this study, we present an algorithm to enable…
Swarm robotic systems are mainly inspired by swarms of socials insects and the collective emergent behavior that arises from their cooperation at the lower lever. Despite the limited sensory ability, computational power, and communication…
Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative…
Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…
Robots are required to autonomously respond to changing situations. Imitation learning is a promising candidate for achieving generalization performance, and extensive results have been demonstrated in object manipulation. However,…
A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the…
In this paper, we propose an approach to the distributed storage and fusion of data for collective perception in resource-limited robot swarms. We demonstrate our approach in a distributed semantic classification scenario. We consider a…
In this paper, we present a machine learning approach to move a group of robots in a formation. We model the problem as a multi-agent reinforcement learning problem. Our aim is to design a control policy for maintaining a desired formation…
Letting robots emulate human behavior has always posed a challenge, particularly in scenarios involving multiple robots. In this paper, we presented a framework aimed at achieving multi-agent reinforcement learning for robot control in…
In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation…
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become…
In recent years, reinforcement learning and its multi-agent analogue have achieved great success in solving various complex control problems. However, multi-agent reinforcement learning remains challenging both in its theoretical analysis…