Search Results for author:
Found 40 papers, 23 papers with code
Language-Conditioned Offline RL for Multi-Robot Navigation
We present a method for developing navigation policies for multi-robot teams that interpret and follow natural language instructions.
CoDreamer: Communication-Based Decentralised World Models
Sample efficiency is a critical challenge in reinforcement learning.
Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
To address this, we introduce Diversity Control (DiCo), a method able to control diversity to an exact value of a given metric by representing policies as the sum of a parameter-shared component and dynamically scaled per-agent components.
Co-Optimization of Environment and Policies for Decentralized Multi-Agent Navigation
By introducing two sub-objectives of multi-agent navigation and environment optimization, we propose an $\textit{agent-environment co-optimization}$ problem and develop a $\textit{coordinated algorithm}$ that alternates between these sub-objectives to search for an optimal synthesis of agent actions and obstacle configurations in the environment; ultimately, improving the navigation performance.
Generalising Multi-Agent Cooperation through Task-Agnostic Communication
Our objective is to learn a fixed-size latent Markov state from a variable number of agent observations.
Revisiting Recurrent Reinforcement Learning with Memory Monoids
Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states.
On the Trade-Off between Stability and Representational Capacity in Graph Neural Networks
Analyzing the stability of graph neural networks (GNNs) under topological perturbations is key to understanding their transferability and the role of each architecture component.
BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
The field of Multi-Agent Reinforcement Learning (MARL) is currently facing a reproducibility crisis.
Docking Multirotors in Close Proximity using Learnt Downwash Models
However, certain missions \textit{require} two multirotors to approach each other within 1-2 body-lengths of each other and hold formation -- we consider one such practical instance: vertically docking two multirotors in the air.
Differentially Private Decentralized Deep Learning with Consensus Algorithms
Furthermore, we show that it is possible to learn a model achieving high accuracies, within 3% of DP-SGD on MNIST under (1, 10^-5)-differential privacy and within 6% of DP-SGD on CIFAR-100 under (10, 10^-5)-differential privacy, without ever sharing raw data with other agents.
Constrained Environment Optimization for Prioritized Multi-Agent Navigation
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.
System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning
In this paper, we introduce System Neural Diversity (SND): a measure of behavioral heterogeneity in multi-agent systems.
Online Control Barrier Functions for Decentralized Multi-Agent Navigation
Control barrier functions (CBFs) enable guaranteed safe multi-agent navigation in the continuous domain.
POPGym: Benchmarking Partially Observable Reinforcement Learning
Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory.
Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learning
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.
Accelerating Multi-Agent Planning Using Graph Transformers with Bounded Suboptimality
Though it is complete and optimal, it does not scale well.
Heterogeneous Multi-Robot Reinforcement Learning
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.
Decentralized Channel Management in WLANs with Graph Neural Networks
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.
Environment Optimization for Multi-Agent Navigation
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.
See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation
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.
VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning
VMAS's scenarios prove challenging in orthogonal ways for state-of-the-art MARL algorithms.
QGNN: Value Function Factorisation with Graph Neural Networks
In multi-agent reinforcement learning, the use of a global objective is a powerful tool for incentivising cooperation.
A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies
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.
Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
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).
Explanation-Aware Experience Replay in Rule-Dense Environments
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.
Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems
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.
The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts
Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances.
Graph Convolutional Memory using Topological Priors
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.
Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection
We demonstrate the performance of our GNN-based learning approach in a scenario of active target tracking with large networks of robots.
ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture
Recent work in the multi-agent domain has shown the promise of Graph Neural Networks (GNNs) to learn complex coordination strategies.
Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control
Robotic simulators are crucial for academic research and education as well as the development of safety-critical applications.
Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning
Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information.
Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication
In this paper, we consider the problem of providing robustness to adversarial communication in multi-agent systems.
Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning
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.
The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning
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
Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning
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.
Graph Neural Networks for Decentralized Multi-Robot Path Planning
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.
Multi-Vehicle Mixed-Reality Reinforcement Learning for Autonomous Multi-Lane Driving
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.
An Adversarial Approach to Private Flocking in Mobile Robot Teams
We present a method that generates private flocking controllers that hide the identity of the leader robot.
Graph Neural Networks for Learning Robot Team Coordination
This paper shows how Graph Neural Networks can be used for learning distributed coordination mechanisms in connected teams of robots.
