no code implementations • 18 May 2023 • Zhan Gao, Amanda Prorok
The goal of this paper is to consider the environment as a decision variable in a system-level optimization problem, where both agent performance and environment cost are incorporated.
1 code implementation • 3 May 2023 • Matteo Bettini, Ajay Shankar, Amanda Prorok
When a system of learning agents is not constrained to homogeneous policies, individual agents may develop diverse behaviors, resulting in emergent complementarity that benefits the system.
no code implementations • 8 Mar 2023 • Zhan Gao, Guang Yang, Amanda Prorok
Such approaches are inefficient and vulnerable to changes in the environment.
1 code implementation • 3 Mar 2023 • Steven Morad, Ryan Kortvelesy, Matteo Bettini, Stephan Liwicki, Amanda Prorok
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory.
no code implementations • 24 Feb 2023 • Ryan Kortvelesy, Steven Morad, Amanda Prorok
The problem of permutation-invariant learning over set representations is particularly relevant in the field of multi-agent systems -- a few potential applications include unsupervised training of aggregation functions in graph neural networks (GNNs), neural cellular automata on graphs, and prediction of scenes with multiple objects.
no code implementations • 20 Jan 2023 • Chenning Yu, QingBiao Li, Sicun Gao, Amanda Prorok
Though it is complete and optimal, it does not scale well.
2 code implementations • 17 Jan 2023 • Matteo Bettini, Ajay Shankar, Amanda Prorok
Through simulations and real-world experiments, we show that: (i) when homogeneous methods fail due to strong heterogeneous requirements, HetGPPO succeeds, and, (ii) when homogeneous methods are able to learn apparently heterogeneous behaviors, HetGPPO achieves higher resilience to both training and deployment noise.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 30 Oct 2022 • Zhan Gao, Yulin Shao, Deniz Gunduz, Amanda Prorok
Wireless local area networks (WLANs) manage multiple access points (APs) and assign scarce radio frequency resources to APs for satisfying traffic demands of associated user devices.
no code implementations • 22 Sep 2022 • Zhan Gao, Amanda Prorok
Traditional approaches to the design of multi-agent navigation algorithms consider the environment as a fixed constraint, despite the obvious influence of spatial constraints on agents' performance.
no code implementations • 1 Aug 2022 • Jan Blumenkamp, QingBiao Li, Binyu Wang, Zhe Liu, Amanda Prorok
We consider the problem of navigating a mobile robot towards a target in an unknown environment that is endowed with visual sensors, where neither the robot nor the sensors have access to global positioning information and only use first-person-view images.
1 code implementation • 7 Jul 2022 • Matteo Bettini, Ryan Kortvelesy, Jan Blumenkamp, Amanda Prorok
VMAS's scenarios prove challenging in orthogonal ways for state-of-the-art MARL algorithms.
1 code implementation • 25 May 2022 • Ryan Kortvelesy, Amanda Prorok
In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation.
2 code implementations • 2 Nov 2021 • Jan Blumenkamp, Steven Morad, Jennifer Gielis, QingBiao Li, Amanda Prorok
We demonstrate our framework on a case-study that requires tight coordination between robots, and present first-of-a-kind results that show successful real-world deployment of GNN-based policies on a decentralized multi-robot system relying on Adhoc communication.
1 code implementation • ICLR 2022 • Benjamin Hudson, QingBiao Li, Matthew Malencia, Amanda Prorok
To close this gap, we present a hybrid data-driven approach for solving the TSP based on Graph Neural Networks (GNNs) and Guided Local Search (GLS).
1 code implementation • 29 Sep 2021 • Francesco Sovrano, Alex Raymond, Amanda Prorok
In this paper, we propose a method for organising experience by means of partitioning the experience buffer into clusters labelled on a per-explanation basis.
no code implementations • 25 Sep 2021 • Amanda Prorok, Matthew Malencia, Luca Carlone, Gaurav S. Sukhatme, Brian M. Sadler, Vijay Kumar
In this survey article, we analyze how resilience is achieved in networks of agents and multi-robot systems that are able to overcome adversity by leveraging system-wide complementarity, diversity, and redundancy - often involving a reconfiguration of robotic capabilities to provide some key ability that was not present in the system a priori.
no code implementations • 26 Jul 2021 • Amanda Prorok, Jan Blumenkamp, QingBiao Li, Ryan Kortvelesy, Zhe Liu, Ethan Stump
Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances.
1 code implementation • 27 Jun 2021 • Steven D. Morad, Stephan Liwicki, Ryan Kortvelesy, Roberto Mecca, Amanda Prorok
Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world.
1 code implementation • 18 May 2021 • Lifeng Zhou, Vishnu D. Sharma, QingBiao Li, Amanda Prorok, Alejandro Ribeiro, Pratap Tokekar, Vijay Kumar
We demonstrate the performance of our GNN-based learning approach in a scenario of active target tracking with large networks of robots.
1 code implementation • 24 Mar 2021 • Ryan Kortvelesy, Amanda Prorok
Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies.
2 code implementations • 3 Mar 2021 • Jacopo Panerati, Hehui Zheng, SiQi Zhou, James Xu, Amanda Prorok, Angela P. Schoellig
Robotic simulators are crucial for academic research and education as well as the development of safety-critical applications.
no code implementations • 29 Dec 2020 • Fernando Gama, QingBiao Li, Ekaterina Tolstaya, Amanda Prorok, Alejandro Ribeiro
Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information.
no code implementations • 1 Dec 2020 • Rupert Mitchell, Jan Blumenkamp, Amanda Prorok
In this paper, we consider the problem of providing robustness to adversarial communication in multi-agent systems.
1 code implementation • 26 Nov 2020 • QingBiao Li, Weizhe Lin, Zhe Liu, Amanda Prorok
Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots.
1 code implementation • 6 Aug 2020 • Jan Blumenkamp, Amanda Prorok
Such a design choice, however, precludes the existence of a single, differentiable communication channel, and consequently prohibits the learning of inter-agent communication strategies.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 11 May 2020 • Binyu Wang, Zhe Liu, Qing-Biao Li, Amanda Prorok
Path planning for mobile robots in large dynamic environments is a challenging problem, as the robots are required to efficiently reach their given goals while simultaneously avoiding potential conflicts with other robots or dynamic objects.
1 code implementation • 12 Dec 2019 • Qing-Biao Li, Fernando Gama, Alejandro Ribeiro, Amanda Prorok
We train the model to imitate an expert algorithm, and use the resulting model online in decentralized planning involving only local communication and local observations.
no code implementations • 26 Nov 2019 • Rupert Mitchell, Jenny Fletcher, Jacopo Panerati, Amanda Prorok
In this article, we present a safe and efficient framework that enables the learning of driving policies for autonomous vehicles operating in a shared workspace, where the absence of collisions cannot be guaranteed.
2 code implementations • 23 Sep 2019 • Hehui Zheng, Jacopo Panerati, Giovanni Beltrame, Amanda Prorok
We present a method that generates private flocking controllers that hide the identity of the leader robot.
no code implementations • 9 May 2018 • Amanda Prorok
This paper shows how Graph Neural Networks can be used for learning distributed coordination mechanisms in connected teams of robots.