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

Abstract

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 learn the optimal control policy. However, existing barrier-based safe learning methods rely on full state feedback. In this paper, an output-feedback safe model-based reinforcement learning technique is developed that utilizes a novel dynamic state estimator to implement simultaneous learning and control for a class of safety-critical systems with partially observable state.

arXiv commentarXiv admin note: substantial text overlap with arXiv:2007.12666

References in corpus (9)

• Approximate Optimal Trajectory Tracking for Continuous Time Nonlinear Systems
• Concurrent learning-based approximate optimal regulation
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
• Model-based reinforcement learning for infinite-horizon approximate optimal tracking
• Efficient model-based reinforcement learning for approximate online optimal
• Safe Exploration in Markov Decision Processes
• Safe Reinforcement Learning in Constrained Markov Decision Processes
• Safe Reinforcement Learning Using Robust Action Governor
• Output-feedback online optimal control for a class of nonlinear systems