arXiv (Cornell University) · 2020 · 43 citations · 13 references
ComputingComputer ScienceRobotics EngineeringMachine LearningRobot ControlRoboticsControl TheoryNeural NetworksPolicy LearningReinforcement LearningRobot SafetySafety-critical SystemsLyapunov ControlLyapunov FunctionsLyapunov-based LearningSafe LearningSafe Policy Learning
This paper develops an approach to learn a policy of a dynamical system that is guaranteed to be both provably safe and goal-reaching. Here, the safety means that a policy must not drive the state of the system to any unsafe region, while the goal-reaching requires the trajectory of the controlled system asymptotically converges to a goal region (a generalization of stability). We obtain the safe and goal-reaching policy by jointly learning two additional certificate functions: a barrier function that guarantees the safety and a developed Lyapunov-like function to fulfill the goal-reaching requirement, both of which are represented by neural networks. We show the effectiveness of the method to learn both safe and goal-reaching policies on various systems, including pendulums, cart-poles, and UAVs.
13
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Reinforcement Learning: An Introduction
IEEE Transactions on Neural Networks · 2005 · 25.8K citations
Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · arXiv (Cornell University) · 2013 · 5.1K citations · Full text
Agnostic Learning with Unknown Utilities
arXiv (Cornell University) · 2016 · 1.4K citations · Full text