Hongpeng Cao
  • Bio
  • Papers
  • Experience
  • Recent & Upcoming Talks
    • Example Talk
  • Publications
    • Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning
    • Simplex-enabled Safe Continual Learning Machine
    • Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning
    • Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
    • 6IMPOSE: Bridging the reality gap in 6D pose estimation for robotic grasping
    • Flexible Gear Assembly with Visual Servoing and Force Feedback
    • Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees
    • Towards safe ai: Sandboxing dnns-based controllers in stochastic games
    • Cloud-edge training architecture for sim-to-real deep reinforcement learning
    • Safe-visor architecture for sandboxing (AI-based) unverified controllers in stochastic cyber--physical systems
  • Projects
  • Blog
    • πŸŽ‰ Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • πŸ“ˆ Communicate your results effectively with the best data visualizations
    • πŸ‘©πŸΌβ€πŸ« Teach academic courses
    • βœ… Manage your projects
  • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Experience
  • Teaching
    • Learn Python

Towards safe ai: Sandboxing dnns-based controllers in stochastic games

Jan 1, 2023Β·
Bingzhuo Zhong
,
Hongpeng Cao
,
Majid Zamani
,
Marco Caccamo
Β· 0 min read
Cite
Type
Conference paper
Publication
Proceedings of the AAAI Conference on Artificial Intelligence
Last updated on Jan 1, 2023
← Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees Jan 1, 2023
Cloud-edge training architecture for sim-to-real deep reinforcement learning Jan 1, 2022 →

Β© {2024} Me. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder β€” the free, open source website builder that empowers creators.