Corpus ID: 30625028

Logically-Constrained Reinforcement Learning

@article{Hasanbeig2018LogicallyConstrainedRL,
  title={Logically-Constrained Reinforcement Learning},
  author={Mohammadhosein Hasanbeig and Alessandro Abate and D. Kroening},
  journal={arXiv: Learning},
  year={2018}
}
  • Mohammadhosein Hasanbeig, Alessandro Abate, D. Kroening
  • Published 2018
  • Mathematics, Computer Science
  • arXiv: Learning
  • We present the first model-free Reinforcement Learning (RL) algorithm to synthesise policies for an unknown Markov Decision Process (MDP), such that a linear time property is satisfied. The given temporal property is converted into a Limit Deterministic Buchi Automaton (LDBA) and a robust reward function is defined over the state-action pairs of the MDP according to the resulting LDBA. With this reward function, the policy synthesis procedure is "constrained" by the given specification. These… CONTINUE READING
    22 Citations
    Certified Reinforcement Learning with Logic Guidance
    • 15
    • PDF
    Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees
    • 24
    • PDF
    Logically-Constrained Neural Fitted Q-Iteration
    • 16
    • PDF
    Logically-Constrained Neural Fitted Q-iteration Extended Abstract
    • PDF
    Reinforcement Learning of Control Policy for Linear Temporal Logic Specifications Using Limit-Deterministic Generalized Büchi Automata
    • 4
    • Highly Influenced
    • PDF
    Formal Policy Synthesis for Continuous-Space Systems via Reinforcement Learning
    • 4
    • PDF
    Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning
    • 16
    • PDF
    Model-based Reinforcement Learning from Signal Temporal Logic Specifications
    • PDF
    Cautious Reinforcement Learning with Logical Constraints
    • 7
    • PDF

    References

    SHOWING 1-10 OF 44 REFERENCES
    Safety-Constrained Reinforcement Learning for MDPs
    • 47
    • PDF
    Correct-by-synthesis reinforcement learning with temporal logic constraints
    • M. Wen, R. Ehlers, U. Topcu
    • Computer Science, Mathematics
    • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2015
    • 37
    • PDF
    Reinforcement learning with temporal logic rewards
    • X. Li, C. Vasile, C. Belta
    • Computer Science
    • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    • 2017
    • 53
    • PDF
    Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints
    • J. Fu, U. Topcu
    • Computer Science, Mathematics
    • Robotics: Science and Systems
    • 2014
    • 106
    • PDF
    A learning based approach to control synthesis of Markov decision processes for linear temporal logic specifications
    • 73
    • Highly Influential
    • PDF
    Model-Based Reinforcement Learning in Continuous Environments Using Real-Time Constrained Optimization
    • 14
    • PDF
    Verification of Markov Decision Processes Using Learning Algorithms
    • 128
    • Highly Influential
    • PDF
    Verification and repair of control policies for safe reinforcement learning
    • 14