7 papers
Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
Silong Yong, Anji Liu, Cunxi Dai +5
A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable traject…
COHORT: Hybrid RL for Collaborative Large DNN Inference on Multi-Robot Systems Under Real-Time Constraints
Mohammad Saeid Anwar, Anuradha Ravi, Indrajeet Ghosh +3
Large deep neural networks (DNNs), especially transformer-based and multimodal architectures, are computationally demanding and challenging to deploy on resource-constrained edge p…
Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning
Indranil Sur, Aswin Raghavan, Abrar Rahman +3
The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managi…
Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning
Peihong Yu, Manav Mishra, Alec Koppel +5
Multi-Agent Reinforcement Learning (MARL) algorithms face the challenge of efficient exploration due to the exponential increase in the size of the joint state-action space. While…
Asynchronous Local Computations in Distributed Bayesian Learning
Kinjal Bhar, He Bai, Jemin George +1
Due to the expanding scope of machine learning (ML) to the fields of sensor networking, cooperative robotics and many other multi-agent systems, distributed deployment of inference…
Reinforcement Learning with an Abrupt Model Change
Wuxia Chen, Taposh Banerjee, Jemin George +1
The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to ach…
Asynchronous Bayesian Learning over a Network
Kinjal Bhar, He Bai, Jemin George +1
We present a practical asynchronous data fusion model for networked agents to perform distributed Bayesian learning without sharing raw data. Our algorithm uses a gossip-based appr…