Safe reinforcement learning with dual robustness
Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can
deteriorate task performance or break down safety specifications. Existing methods either …
deteriorate task performance or break down safety specifications. Existing methods either …
Robust Approximate Dynamic Programming for Nonlinear Systems With Both Model Error and External Disturbance
J Li, R Nagamune, Y Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Model error and external disturbance have been separately addressed by optimizing the
definite performance in standard linear control problems. However, the concurrent handling …
definite performance in standard linear control problems. However, the concurrent handling …
Physics‐informed reinforcement learning for optimal control of nonlinear systems
Y Wang, Z Wu - AIChE Journal, 2024 - Wiley Online Library
This article proposes a model‐free framework to solve the optimal control problem with an
infinite‐horizon performance function for nonlinear systems with input constraints …
infinite‐horizon performance function for nonlinear systems with input constraints …
A Time-Aggregated Model-Free RL Algorithm for Optimal Containment Control of MASs
In this paper, the optimal containment control problem for a class of unknown nonlinear multi-
agent systems (MASs) is studied via a time-aggregated (TA) model-free reinforcement …
agent systems (MASs) is studied via a time-aggregated (TA) model-free reinforcement …