MShabani8 / RL_tracking_PI_algorithm_single_agent
the code implements a training algorithm for a tracking control system using dynamic programming and reinforcement learning. It uses neural networks to approximate the control policy and iteratively updates the networks to improve the system's performance.
☆17Updated last year
Alternatives and similar repositories for RL_tracking_PI_algorithm_single_agent:
Users that are interested in RL_tracking_PI_algorithm_single_agent are comparing it to the libraries listed below
- Reinforcement Learning (RL) Course in MATLAB with exercises and solutions☆12Updated 3 years ago
- Contains all research-related code for publications by Brent Wallace, Arizona State University☆12Updated 2 years ago
- MATLAB simulation and final report/presentation for M.S. thesis. "Adaptive Dynamic Programming for Human Postural Balance Control"☆14Updated 6 years ago
- Implementation of Single-Agent and Multi-Agent Reinforcement Learning Algorithms. MATLAB.☆67Updated 6 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)☆15Updated 5 years ago
- Codes reproducing paper Jongeun Choi, Songhwai Oh, Roberto Horowitz, Distributed learning and cooperative control for multi-agent systems…☆21Updated 3 years ago
- Several ADP algorithms code for the data-driven optimal control of linear time-varying systems☆18Updated 2 years ago
- Implementation of a paper on adaptive optimal control (solving ARE) based on policy iterations☆28Updated 5 years ago
- This repository represents an implementation of suggested distributed control algorithm for formation control of multi-agent system with …☆22Updated 2 years ago
- A simple and short implementation of the Q-Learning Reinforcement Algorithm in Matlab☆47Updated 9 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…☆13Updated 4 years ago
- Reinforcement based gain calculation for a tracking LQR using actor-critic method☆21Updated 4 years ago
- Introduction to Reinforcement Learning and Model Predictive Control with MATLAB and Simulink☆23Updated last year
- Comparing the performance of a DDPG Reinforcement learning model to control temperature with that of a PID and a thermostat controller.☆45Updated last year
- Adaptive dynamic programming☆107Updated 2 months ago
- A discrete Nash equilibrium seeking algorithm for multi-agent systems☆10Updated 4 years ago
- Code for paper: Event-triggered deep reinforcement learning using parallel control: A case study in autonomous driving.☆19Updated last year
- Model-free event-triggered optimal control with performance guarantees via goal representation heuristic dynamic programming☆13Updated 3 years ago
- Zhao-Jichao / Distributed_optimal_-formation_control_of_heterogeneous_multi-agent_systems_with_mixed-orders异构混合阶多智能体系统编队控制的分布式优化☆31Updated 3 years ago
- Implementation of Reinforcement learning using Q learning algorithm- Robot in Maze - Matlab☆28Updated 5 years ago
- This research compared three reinforcement learning (RL) algorithms (SAC, PPO, DDPG) to traditional PID control for water level control i…☆16Updated 5 months ago
- ☆20Updated 2 years ago
- We propose a novel data-driven optimal adaptive fault-tolerant control method for path tracking control.☆16Updated 8 months ago
- 包括UGV和UAV在内的异构混合阶多智能体系统的一致性☆22Updated 3 years ago
- RL implementation in course 'Control for Robotics' at U of T, includes Generalized Policy Iteration, Monte Carlo and Q-Learning in MATLAB☆13Updated 2 years ago
- A MATLAB Class for convenient ADP simulation☆22Updated 7 years ago
- consensus and synchronization algorithms of networked multi agent systems with event triggered communications☆34Updated last year
- Adaptive dynamic programming(ADP) 自适应动态规划☆42Updated 4 years ago
- course project: a simple implementation of Q learning and MPC☆17Updated 3 years ago
- Tube based Model Predictive Control that utilize Neural Networks to improve performance with adaptive control inputs.☆18Updated 3 years ago