Probabilistic guarantees for safe deep reinforcement learning

DOI10.1007/978-3-030-57628-8_14OpenAlexW3082528606MaRDI QIDQ1996032

Yanyan Li

Publication date: 2 March 2021

Full work available at URL: https://arxiv.org/abs/2005.07073

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Related Items (2)

DMPC: a data-and model-driven approach to predictive control ⋮ Probabilistic guarantees for safe deep reinforcement learning

Cites Work

• Unnamed Item
• Unnamed Item
• A game-based abstraction-refinement framework for Markov decision processes
• Probabilistic guarantees for safe deep reinforcement learning
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Formal Verification and Synthesis for Discrete-Time Stochastic Systems
• Verification of Markov Decision Processes Using Learning Algorithms
• Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Omega-Regular Objectives in Model-Free Reinforcement Learning

This page was built for publication: Probabilistic guarantees for safe deep reinforcement learning