Certified reinforcement learning with logic guidance
From MaRDI portal
Publication:6136089
Abstract: Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying requirements as tasks or goals. We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs). The given LTL property is translated into a Limit-Deterministic Generalised Buchi Automaton (LDGBA), which is then used to shape a synchronous reward function on-the-fly. Under certain assumptions, the algorithm is guaranteed to synthesise a control policy whose traces satisfy the LTL specification with maximal probability.
Cites work
- scientific article; zbMATH DE number 3128787 (Why is no real title available?)
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- scientific article; zbMATH DE number 1350309 (Why is no real title available?)
- scientific article; zbMATH DE number 7088727 (Why is no real title available?)
- scientific article; zbMATH DE number 5585443 (Why is no real title available?)
- scientific article; zbMATH DE number 2243395 (Why is no real title available?)
- A comprehensive survey on safe reinforcement learning
- A stochastic approximation method for reachability computations
- Analysis of a Numerical Dynamic Programming Algorithm Applied to Economic Models
- Approximation of Markov decision processes with general state space
- Automated verification and synthesis of stochastic hybrid systems: a survey
- Certified reinforcement learning with logic guidance
- Complementing semi-deterministic Büchi automata
- Continuous state dynamic programming via nonexpansive approximation
- Convergence of discretization procedures in dynamic programming
- Cost-efficient numerical algorithm for solving the linear inverse problem of finding a variable magnetization
- Deep reinforcement learning with temporal logics
- Deterministic generators and games for LTL fragments
- Differential dynamic logic for hybrid systems
- Discounting the distant future: How much do uncertain rates increase valuations?
- Explorations in Monte Carlo Methods
- Learning-Based Probabilistic LTL Motion Planning With Environment and Motion Uncertainties
- Limit deterministic and probabilistic automata for \(\mathrm{LTL}\backslash GU\)
- Limit-deterministic Büchi automata for linear temporal logic
- Markov decision processes with state-dependent discount factors and unbounded rewards/costs
- Model checking of safety properties
- Multilayer feedforward networks are universal approximators
- Near-optimal reinforcement learning in polynomial time
- Optimal Translation of LTL to Limit Deterministic Automata
- Probabilistic reachability and safety for controlled discrete time stochastic hybrid systems
- Quantitative automata-based controller synthesis for non-autonomous stochastic hybrid systems
- Quantitative model-checking of controlled discrete-time Markov processes
- Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes
- Safe Exploration of State and Action Spaces in Reinforcement Learning
- Statistical verification of probabilistic properties with unbounded until
- StocHy - automated verification and synthesis of stochastic processes
- Variable resolution discretization in optimal control
- Verification of Markov decision processes using learning algorithms
- Verification of general Markov decision processes by approximate similarity relations and policy refinement
- \({\mathcal Q}\)-learning
- \textsf{AMYTISS}: parallelized automated controller synthesis for large-scale stochastic systems
Cited in
(4)
This page was built for publication: Certified reinforcement learning with logic guidance
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136089)
