Learning Optimal Strategies for Temporal Tasks in Stochastic Games
Not on the map. Why?
Abstract (arXiv)
Synthesis from linear temporal logic (LTL) specifications provides assured controllers for systems operating in stochastic and potentially adversarial environments. Automatic synthesis tools, however, require a model of the environment to construct controllers. In this work, we introduce a model-free reinforcement learning (RL) approach to derive controllers from given LTL specifications even when the environment is completely unknown. We model the problem as a stochastic game (SG) between the controller and the adversarial environment; we then learn optimal control strategies that maximize the probability of satisfying the LTL specifications against the worst-case environment behavior. We first construct a product game using the deterministic parity automaton (DPA) translated from the given LTL specification. By deriving distinct rewards and discount factors from the acceptance condition of the DPA, we reduce the maximization of the worst-case probability of satisfying the LTL specification into the maximization of a discounted reward objective in the product game; this enables the use of model-free RL algorithms to learn an optimal controller strategy. To deal with the common scalability problems when the number of sets defining the acceptance condition of the DPA (usually referred as colors), is large, we propose a lazy color generation method where distinct rewards and discount factors are utilized only when needed, and an approximate method where the controller eventually focuses on only one color. In several case studies, we show that our approach is scalable to a wide range of LTL formulas, significantly outperforming existing methods for learning controllers from LTL specifications in SGs.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 85 references that are in the map. First posted on arXiv 8 Feb 2021.
Builds on
23 of 85 references.
References · 23
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2016OpenAI Gymcited by 1,684
- 2017Safe Reinforcement Learning via Shieldingcited by 427
- 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
- 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 154
- 2016Reinforcement Learning With Temporal Logic Rewardscited by 114
- 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
- 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 74
- 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 74
- 2014Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraintscited by 53
- 2014A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specificationscited by 49
- 2014Verification of Markov Decision Processes using Learning Algorithmscited by 38
11 more
- 2019PAC Statistical Model Checking for Markov Decision Processes and Stochastic Gamescited by 30
- 2019Reinforcement Learning with Probabilistic Guarantees for Autonomous Drivingcited by 27
- 2020Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized B"uchi Automatacited by 11
- 2020Model-Free Reinforcement Learning for Stochastic Games with Linear Temporal Logic Objectivescited by 6
- 2013Symbolic control of stochastic systems via approximately bisimilar finite abstractionscited by 4
- 2017From LTL and Limit-Deterministic B"uchi Automata to Deterministic Parity Automatacited by 4
- 2014Temporal Logic Control for Stochastic Linear Systems using Abstraction Refinement of Probabilistic Gamescited by 2
- 2020Secure Planning Against Stealthy Attacks via Model-Free Reinforcement Learningcited by 2
- 2017Formal Methods for Adaptive Control of Dynamical Systemscited by 1
- 2019Security-Aware Synthesis Using Delayed-Action Gamescited by 1
- 2019Optimal Secure Control with Linear Temporal Logic Constraintscited by 1
Built on by
Citing papers per year: 2024: 2; 2025: 0; 2026: 1.
3 papers.