mahaitongdae
I am a PhD student at Harvard SEAS. I am working on safe control and reinforcement learning with application to robotics.
@lina-robotics-lab at Harvard SEASAllston, MA
Pinned Repositories
Approximate-Dynamic-Programming
ADP demo code for Reinforcement Learning and Control, Tsinghua Univ. Lecture Notes.
dbo
Distributed Bayesian Optimization for Multi-Agent Systems
Deep-reinforcement-learning-with-pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Feasible-Actor-Critic
Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.
Reachability_Constrained_RL
Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.
RLC-project
Project for Prof. Shengbo Eben Li's Reinforcement Learning and Control course in Tsinghua University.
safe-control-gym
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
safe_exp_env
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 Barrier Function
safety-starter-agents
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
Safety_Index_Synthesis
Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.
mahaitongdae's Repositories
mahaitongdae/mahaitongdae
Config files for my GitHub profile.
mahaitongdae/crazyswarm
A Large Quadcopter Swarm
mahaitongdae/koopman_learning_and_control
Repository for Koopman based learning and nonlinear control
mahaitongdae/SafeOpt
Safe Bayesian Optimization
mahaitongdae/Universal_Robots_ROS_Driver
Universal Robots ROS driver supporting CB3 and e-Series
mahaitongdae/pycma
Python implementation of CMA-ES
mahaitongdae/Reachability_Constrained_RL
Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.
mahaitongdae/mahaitongdae.github.io
mahaitongdae/toyota_exp_train
mahaitongdae/safety-starter-agents
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
mahaitongdae/Feasible-Actor-Critic
Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.
mahaitongdae/Approximate-Dynamic-Programming
ADP demo code for Reinforcement Learning and Control, Tsinghua Univ. Lecture Notes.
mahaitongdae/la-mbda
LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization
mahaitongdae/Safe-Reinforcement-Learning-Baseline
The repository is for safe reinforcement learning baselines.
mahaitongdae/crabs
Code for Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
mahaitongdae/phd-bibliography
References on Optimal Control, Reinforcement Learning and Motion Planning
mahaitongdae/Max-value-Entropy-Search
Max-value Entropy Search for Efficient Bayesian Optimization
mahaitongdae/dcrl
Density Constrained Reinforcement Learning
mahaitongdae/Feasible-Policy-Optimization
mahaitongdae/safe-control-gym
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
mahaitongdae/hj_reachability
Hamilton-Jacobi reachability analysis in JAX.
mahaitongdae/mpg
MPG is originated from the paper "Mixed policy gradient", which also contains a cluster of high-quality implementations of deep reinforcement learning algorithms.
mahaitongdae/recovery-rl
Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.
mahaitongdae/experiment_driving
Real Vehicle Experiment for Integrated decision and control framwork
mahaitongdae/safety_rl
mahaitongdae/Kalman-and-Bayesian-Filters-in-Python
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
mahaitongdae/optimized_dp
Optimizing Dynamic Programming-Based Algorithms
mahaitongdae/safe_exp_env
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 Barrier Function
mahaitongdae/Carla-ppo
This repository hosts a customized PPO based agent for Carla. The goal of this project is to make it easier to interact with and experiment in Carla with reinforcement learning based agents -- this, by wrapping Carla in a gym like environment that can handle custom reward functions, custom debug output, etc.
mahaitongdae/RLC-project
Project for Prof. Shengbo Eben Li's Reinforcement Learning and Control course in Tsinghua University.