• Corpus ID: 238253364

Safety aware model-based reinforcement learning for optimal control of a class of output-feedback nonlinear systems

  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},
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… 

Safe Controller for Output Feedback Linear Systems using Model-Based Reinforcement Learning

Simulation results indicate that barrier transformation is an effective approach to achieve online reinforcement learning in safety-critical systems using output feedback.



Safe Model-Based Reinforcement Learning for Systems With Parametric Uncertainties

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.

Safe Reinforcement Learning Using Robust Action Governor

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

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

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

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

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

Reinforcement Learning for Partially Observable Dynamic Processes: Adaptive Dynamic Programming Using Measured Output Data

  • F. LewisK. Vamvoudakis
  • Computer Science
    IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2011
It is shown that, similar to Q-learning, the new methods have the important advantage that knowledge of the system dynamics is not needed for the implementation of these learning algorithms or for the OPFB control.