Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems
@article{Mahmud2021SafetyAM, title={Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems}, author={S. M. Nahid Mahmud and Moad Abudia and Scott A. Nivison and Zachary I. Bell and Rushikesh Kamalapurkar}, journal={ArXiv}, year={2021}, volume={abs/2110.00271} }
The ability to learn and execute optimal control policies safely is critical to realization of complex autonomy, especially where task restarts are not available and/or the systems are safety-critical. Safety requirements are often expressed in terms of state and/or control constraints. Methods such as barrier transformation and control barrier functions have been successfully used, in conjunction with model-based reinforcement learning, for safe learning in systems under state constraints, to…
Figures and Tables from this paper
One Citation
Safe Controller for Output Feedback Linear Systems using Model-Based Reinforcement Learning
- Computer ScienceArXiv
- 2022
Simulation results indicate that barrier transformation is an effective approach to achieve online reinforcement learning in safety-critical systems using output feedback.
References
SHOWING 1-10 OF 55 REFERENCES
Safe Model-Based Reinforcement Learning for Systems With Parametric Uncertainties
- Computer ScienceFrontiers in Robotics and AI
- 2021
A model-based reinforcement learning technique that utilizes a novel filtered concurrent learning method, along with a barrier transformation, is developed in this paper to realize simultaneous learning of unknown model parameters and approximate optimal state-constrained control policies for safety-critical systems.
Safety-Aware Reinforcement Learning Framework with an Actor-Critic-Barrier Structure
- Mathematics2019 American Control Conference (ACC)
- 2019
The actor-critic based reinforcement learning technique is combined with the barrier transformation to learn the optimal control policy that considers both the full-state constraints and input saturations.
Safe Reinforcement Learning Using Robust Action Governor
- Computer ScienceL4DC
- 2021
A framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning is introduced.
Safe Reinforcement Learning: Learning with Supervision Using a Constraint-Admissible Set
- Computer Science2018 Annual American Control Conference (ACC)
- 2018
A novel safe RL framework that guarantees safety during learning by exploiting a constraint-admissible set for supervision is developed and demonstrated in an adaptive cruise control example where a nonlinear fuel economy cost function is optimized without violating system constraints.
A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
- Computer ScienceIEEE Transactions on Automatic Control
- 2019
A general safety framework based on Hamilton–Jacobi reachability methods that can work in conjunction with an arbitrary learning algorithm is proposed, which proves theoretical safety guarantees combining probabilistic and worst-case analysis and demonstrates the proposed framework experimentally on a quadrotor vehicle.
Model-based reinforcement learning for output-feedback optimal control of a class of nonlinear systems
- Engineering2019 American Control Conference (ACC)
- 2019
An output-feedback model-based reinforcement learning (MBRL) method for a class of second-order nonlinear systems is developed that uses exact model knowledge and integrates a dynamic state estimator within the model- based reinforcement learning framework.
Model-Based Reinforcement Learning for Infinite-Horizon Approximate Optimal Tracking
- MathematicsIEEE Transactions on Neural Networks and Learning Systems
- 2017
This brief paper provides an approximate online adaptive solution to the infinite-horizon optimal tracking problem for control-affine continuous-time nonlinear systems with unknown drift dynamics. To…
Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
- Computer ScienceAutom.
- 2014
Online barrier-actor-critic learning for H∞ control with full-state constraints and input saturation
- EngineeringJ. Frankl. Inst.
- 2020