Deep reinforcement learning with temporal logics

DOI10.1007/978-3-030-57628-8_1zbMath1455.68190OpenAlexW3080598349MaRDI QIDQ1996007

Daniel Kroening, Alessandro Abate, Mohammadhosein Hasanbeig

Publication date: 2 March 2021

Full work available at URL: https://doi.org/10.1007/978-3-030-57628-8_1

zbMATH Keywords

linear temporal logicdeep learningcontinuous-action Markov decision processescontinuous-state Markov decision processesmodel-free reinforcement learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Logic in artificial intelligence (68T27) Automata and formal grammars in connection with logical questions (03D05) Temporal logic (03B44)

Related Items (13)

Enforcing almost-sure reachability in POMDPs ⋮ Planning for potential: efficient safe reinforcement learning ⋮ Temporal logic guided safe model-based reinforcement learning: a hybrid systems approach ⋮ Dynamic shielding for reinforcement learning in black-box environments ⋮ A framework for transforming specifications in reinforcement learning ⋮ Certified reinforcement learning with logic guidance ⋮ Specification-guided reinforcement learning ⋮ Verifiably safe exploration for end-to-end reinforcement learning ⋮ Deep reinforcement learning with temporal logics ⋮ Unnamed Item ⋮ Automated verification and synthesis of stochastic hybrid systems: a survey ⋮ Learning that grid-convenience does not hurt resilience in the presence of uncertainty ⋮ Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov decision processes with state-dependent discount factors and unbounded rewards/costs
• Approximate model checking of stochastic hybrid systems
• Stochastic optimal control. The discrete time case
• Discounting the distant future: How much do uncertain rates increase valuations?
• Near-optimal reinforcement learning in polynomial time
• \({\mathcal Q}\)-learning
• Deep reinforcement learning with temporal logics
• Verification of Markov Decision Processes Using Learning Algorithms
• Limit-Deterministic Büchi Automata for Linear Temporal Logic
• Omega-Regular Objectives in Model-Free Reinforcement Learning
• Verifiably Safe Off-Model Reinforcement Learning

This page was built for publication: Deep reinforcement learning with temporal logics