Skip to content
View mahaitongdae's full-sized avatar
👽
👽
71 followers · 14 following

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2

Achievements

Achievement: StarstruckAchievement: Pull Sharkx2

Block or report mahaitongdae

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mahaitongdae/README.md
  • 👋 Hi, I’m Haitong Ma @mahaitongdae. DAE represents the old name of my undergraduate department, department of automotive engineering. It is now School of Vehicle and Mobility at Tsinghua University. After graduating from Tsinghua University, I am fortunate to pursue my PhD at Harvard SEAS working with Prof. Na Li.
  • 👀 I’m interested in the intersection between control, learning and optimization, and broad areas where these techniques could be applied to.
  • 📄 My previous research mostly focus on developing provable learning-based safety guarantees for dynamical systems (by CBF or reachability analysis) using reinforcement learning.
  • 🌱 I’m currently learning about the crazyflies, which is an open-sourced quadrotor developed by Bitcraze.
  • 📫 Feel free to reach me through issues and email!

Haitong's GitHub stats

Pinned Loading

  1. Reachability_Constrained_RL Reachability_Constrained_RL Public

    Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.

    Python 30 4

  2. Safety_Index_Synthesis Safety_Index_Synthesis Public

    Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.

    Python 13 2

  3. Feasible-Actor-Critic Feasible-Actor-Critic Public

    Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.

    Python 16 3

  4. Approximate-Dynamic-Programming Approximate-Dynamic-Programming Public

    ADP demo code for Reinforcement Learning and Control, Tsinghua Univ. Lecture Notes.

    Python 39 11

  5. safe_exp_env safe_exp_env Public

    Thrid-party safety-gym safe exploration environments for autonomous driving. Also environment used for IROS 2021 paper: Model-based Constrained Reinforcement Learning using Generalized Control Barr…

    Python 28 5

  6. dbo dbo Public

    Forked from FilipKlaesson/dbo

    Distributed Bayesian Optimization for Multi-Agent Systems

    Jupyter Notebook 2