Haitong Ma's repositories
Approximate-Dynamic-Programming
ADP demo code for Reinforcement Learning and Control, Tsinghua Univ. Lecture Notes.
Reachability_Constrained_RL
Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.
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
Feasible-Actor-Critic
Code for paper Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety.
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
safety-starter-agents
Basic constrained RL agents used in experiments for the "Benchmarking Safe Exploration in Deep Reinforcement Learning" paper.
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.
experiment_driving
Real Vehicle Experiment for Integrated decision and control framwork
crabs
Code for Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
crazyswarm
A Large Quadcopter Swarm
dcrl
Density Constrained Reinforcement Learning
hj_reachability
Hamilton-Jacobi reachability analysis in JAX.
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.
koopman_learning_and_control
Repository for Koopman based learning and nonlinear control
la-mbda
LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization
mahaitongdae
Config files for my GitHub profile.
Max-value-Entropy-Search
Max-value Entropy Search for Efficient Bayesian Optimization
optimized_dp
Optimizing Dynamic Programming-Based Algorithms
phd-bibliography
References on Optimal Control, Reinforcement Learning and Motion Planning
pycma
Python implementation of CMA-ES
recovery-rl
Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.
Safe-Reinforcement-Learning-Baseline
The repository is for safe reinforcement learning baselines.
SafeOpt
Safe Bayesian Optimization
Universal_Robots_ROS_Driver
Universal Robots ROS driver supporting CB3 and e-Series