Specification-guided reinforcement learning

DOI10.1007/978-3-031-22308-2_1MaRDI QIDQ6164418zbMATH OpenFDO

Authors Suguman Bansal

Publication date 28 July 2023

Published in Static Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-22308-2_1

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A framework for transforming specifications in reinforcement learning
• Deep reinforcement learning with temporal logics
• Policy synthesis and reinforcement learning for discounted LTL
• Maximum causal entropy specification inference from demonstrations
• Extended Markov games to learn multiple tasks in multi-agent reinforcement learning

Cites work

• Deep reinforcement learning with temporal logics
• End-to-end training of deep visuomotor policies
• Faithful and Effective Reward Schemes for Model-Free Reinforcement Learning of Omega-Regular Objectives
• Model-Free Reinforcement Learning for Stochastic Parity Games
• Near-optimal reinforcement learning in polynomial time
• Omega-Regular Objectives in Model-Free Reinforcement Learning
• Reinforcement learning. An introduction
• Specification-Guided Learning of Nash Equilibria with High Social Welfare

Cited in

(6)

• A human-centered data-driven planner-actor-critic architecture via logic programming
• A framework for transforming specifications in reinforcement learning
• Learning through imitation by using formal verification
• Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective
• Specification-Guided Learning of Nash Equilibria with High Social Welfare
• Policy synthesis and reinforcement learning for discounted LTL

This page was built for publication: Specification-guided reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6164418)