Improved communication efficiency in federated natural policy gradient via admm-based gradient updates
Federated reinforcement learning (FedRL) enables agents to collaboratively train a global
policy without sharing their individual data. However, high communication overhead …
policy without sharing their individual data. However, high communication overhead …
Model-free learning with heterogeneous dynamical systems: A federated LQR approach
We study a model-free federated linear quadratic regulator (LQR) problem where M agents
with unknown, distinct yet similar dynamics collaboratively learn an optimal policy to …
with unknown, distinct yet similar dynamics collaboratively learn an optimal policy to …
Finite-time analysis of on-policy heterogeneous federated reinforcement learning
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing
the sample complexity of reinforcement learning tasks by exploiting information from …
the sample complexity of reinforcement learning tasks by exploiting information from …
[HTML][HTML] Wireless control: Retrospective and open vistas
The convergence of wireless networks and control engineering has been a technological
driver since the beginning of this century. It has significantly contributed to a wide set of …
driver since the beginning of this century. It has significantly contributed to a wide set of …
Imitation and transfer learning for LQG control
In this letter we study an imitation and transfer learning setting for Linear Quadratic Gaussian
(LQG) control, where (i) the system dynamics, noise statistics and cost function are unknown …
(LQG) control, where (i) the system dynamics, noise statistics and cost function are unknown …
Meta-learning operators to optimality from multi-task non-iid data
A powerful concept behind much of the recent progress in machine learning is the extraction
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
Fleet Policy Learning via Weight Merging and An Application to Robotic Tool-Use
Fleets of robots ingest massive amounts of streaming data generated by interacting with
their environments, far more than those that can be stored or transmitted with ease. At the …
their environments, far more than those that can be stored or transmitted with ease. At the …
Multi-task system identification of similar linear time-invariant dynamical systems
Y Chen, AM Ospina, F Pasqualetti… - 2023 62nd IEEE …, 2023 - ieeexplore.ieee.org
This paper presents a system identification framework-inspired by multi-task learning-to
estimate the dynamics of a given number of linear time-invariant (LTI) systems jointly by …
estimate the dynamics of a given number of linear time-invariant (LTI) systems jointly by …
Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
A powerful concept behind much of the recent progress in machine learning is the extraction
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
of common features across data from heterogeneous sources or tasks. Intuitively, using all of …
Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for the Model-free LQR
We investigate the problem of learning Linear Quadratic Regulators (LQR) in a multi-task,
heterogeneous, and model-free setting. We characterize the stability and personalization …
heterogeneous, and model-free setting. We characterize the stability and personalization …