Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation

Abstract

Deep reinforcement learning (DRL) has attracted much attention as an approach to solve optimal control problems without mathematical models of systems. On the other hand, in general, constraints may be imposed on optimal control problems. In this study, we consider the optimal control problems with constraints to complete temporal control tasks. We describe the constraints using signal temporal logic (STL), which is useful for time sensitive control tasks since it can specify continuous signals within bounded time intervals. To deal with the STL constraints, we introduce an extended constrained Markov decision process (CMDP), which is called a $\tau$-CMDP. We formulate the STL-constrained optimal control problem as the $\tau$-CMDP and propose a two-phase constrained DRL algorithm using the Lagrangian relaxation method. Through simulations, we also demonstrate the learning performance of the proposed algorithm.

arXiv comment16 pages, 20 figures, accepted for IEEE Access

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Continuous control with deep reinforcement learning
• Addressing Function Approximation Error in Actor-Critic Methods
• Soft Actor-Critic Algorithms and Applications
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Learning to Walk in the Real World with Minimal Human Effort
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic
• Logically-Constrained Reinforcement Learning
• Modular Deep Reinforcement Learning with Temporal Logic Specifications
• Tractable Reinforcement Learning of Signal Temporal Logic Objectives

Cited by in corpus (1)

• Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning