xiangyu-liu / PG4LQR
Model-free policy gradient algorithm for LQR
☆10Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for PG4LQR
- ADP demo code for Reinforcement Learning and Control, Tsinghua Univ. Lecture Notes.☆39Updated 2 years ago
- 关于书《强化学习第二版》（作者Richard S. Sutton）每章节的代码实现（matlab版）☆14Updated 5 years ago
- Implementation of Reinforcement learning using Q learning algorithm- Robot in Maze - Matlab☆28Updated 4 years ago
- A data-driven method for linear quadratic control with state and control constraints☆8Updated 2 years ago
- MATLAB simulation and final report/presentation for M.S. thesis. "Adaptive Dynamic Programming for Human Postural Balance Control"☆12Updated 6 years ago
- Code for the paper {Pang, Bo, and Zhong-Ping Jiang. "Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic …☆18Updated 2 years ago
- An Off-policy Reinforcement Learning Algorithm for Optimal Tracking Control Problem☆13Updated 8 months ago
- Implementation of Single-Agent and Multi-Agent Reinforcement Learning Algorithms. MATLAB.☆60Updated 6 years ago
- Adaptive dynamic programming（ADP） 自适应动态规划☆37Updated 4 years ago
- the code implements a training algorithm for a tracking control system using dynamic programming and reinforcement learning. It uses neur…☆10Updated last year
- Approximate Dynamic Programming exercises from Powell (2011)☆12Updated last year
- Approximate dynamic programming (ADP) and Policy gradient (PG) based sequential optimal experimental design (sOED)☆15Updated 2 years ago
- Adaptive dynamic programming☆72Updated this week
- ☆11Updated 7 months ago
- Reinforcement learning Algorithms such as SARSA, Q learning, Actor-Critic Policy Gradient and Value Function Approximation were applied t…☆104Updated 2 years ago
- ☆41Updated 3 years ago
- This repository contains two new algorithms: KPIRL and KLA. KPIRL is a non-linear extension to Abbeel and Ng's Projection IRL algorithm (…☆8Updated last year
- Implementation of Incremental Heuristic Dynamic Programming with Neural Networks as Actor and Critic function appoximators.☆11Updated last year
- A modular MATLAB toolkit for Dynamic programming (DP) and Approximate Dynamic Programming (ADP) for Adaptive Modeling and Optimization☆45Updated 5 years ago
- Implementation of a paper on adaptive optimal control (solving ARE) based on policy iterations☆23Updated 5 years ago
- We present a new comparative study of the paper from Hansson and Boyd Robust Optimal Control of Linear Discrete-Time Systems using Primal…☆12Updated 4 years ago
- RL implementation in course 'Control for Robotics' at U of T, includes Generalized Policy Iteration, Monte Carlo and Q-Learning in MATLAB☆10Updated 2 years ago
- course project: a simple implementation of Q learning and MPC☆12Updated 3 years ago
- ☆9Updated 6 years ago
- This repository includes a realization of the resilient projection-based consensus actor-critic algorithm that is resilient to adversaria…☆10Updated 2 years ago
- ☆29Updated 5 years ago
- Several ADP algorithms code for the data-driven optimal control of linear time-varying systems☆13Updated 2 years ago
- ☆57Updated 2 years ago
- Contains all research-related code for publications by Brent Wallace, Arizona State University☆10Updated last year