Applications
Examples of how to apply reinforcement learning
Reinforcement learning can be applied to a variety of problems in different fields, such as control, robotics, scheduling, optimization, and finance. Here are some examples.
Tutorials
- Control Water Level in a Tank Using a DDPG Agent
Train a controller using reinforcement learning with a plant modeled in Simulink® as the training environment. - Tune Single PI Controller Gains For Multiple Operating Points Using Reinforcement Learning
Tune the gains of a PI controller using a TD3 agent. - Train SAC Agent for Ball Balance Control
Train a SAC agent to balance a ball on a flat surface using a robot arm. - Train Default TD3 Agent to Control Quanser QUBE Pendulum
Train a TD3 agent to balance the Quanser QUBE rotational inverted pendulum. - Train Reinforcement Learning Agent Offline to Control Quanser QUBE Pendulum
Train TD3 agent offline to control a Quanser QUBE pendulum. - Train TD3 Agent for PMSM Control
Train a TD3 agent to control the currents in a permanent magnet synchronous motor. - Field-Oriented Control of PMSM Using Reinforcement Learning (Motor Control Blockset)
This example shows you how to use the control design method of reinforcement learning to implement field-oriented control (FOC) of a permanent magnet synchronous motor (PMSM). - Train DQN Agent with LSTM Network to Control House Heating System
Train a DQN agent with a recurrent network to control the temperature of an house. - Train Reinforcement Learning Agent with Constraint Enforcement (Simulink Control Design)
Train a reinforcement learning agent with actions constrained using the Constraint Enforcement block. - Create and Train Custom LQR Agent
Create a custom agent that solves an LQR problem and train it using the built-in train function. - Train DDPG Agent to Control Two-Thruster Sliding Vehicle
Train a DDPG agent to control a robot sliding over a frictionless 2-D plane. - Train Default PPO Agent for Discrete Lander Vehicle
Train a default PPO agent to land a discrete action space flying vehicle. - Train Soft Actor Critic Agent with Custom Networks for Discrete Lander Vehicle
Train a SAC agent to land a discrete action space flying vehicle. - Train Biped Robot to Walk Using Reinforcement Learning Agents
Compare DDPG and TD3 agent for the control a biped walking robot modeled in Simscape™ Multibody™. - Add Safety Constraint to Simulate Two-Link Robot with SAC Agent
Add high-order barrier function to safely simulate a two-link robot model with a SAC agent. - Train Biped Robot to Walk Using Evolution Strategy-Reinforcement Learning Agents
Train TD3 agent using evolutionary strategy. - Quadruped Robot Locomotion Using DDPG Agent
Train a DDPG agent to control a quadruped walking robot modeled in Simscape Multibody. - Generate Reward Function from a Model Predictive Controller for a Servomotor
Generate a reward function from an MPC controller applied to a servomotor and use it to train a TD3 agent. - Generate Reward Function from a Model Verification Block for a Water Tank System
Generate a reward function from an model verification block applied to a water tank system and use it to train a TD3 agent. - Imitate MPC Controller for Lane Keeping Assist
Train a deep neural network to imitate the behavior of a model predictive controller within a lane keeping assist system. - Imitate Nonlinear MPC Controller for Sliding Robot
Train a deep neural network to imitate the behavior of a nonlinear model predictive controller for a robot siding on a 2-D frictionless plane. - Train DDPG Agent with Pretrained Actor Network
Train a DDPG agent using an actor network that has been previously trained using supervised learning. - Train DQN Agent for Lane Keeping Assist
Train a DQN agent for a lane keeping assist application. - Train PPO Agent with Curriculum Learning for a Lane Keeping Application
Train a PPO agent for a lane keeping assist task by gradually increasing task complexity. - Train DDPG Agent for Adaptive Cruise Control
Train a DDPG agent for an adaptive cruise control application. - Train DDPG Agent for Path-Following Control
Train a DDPG agent for lane following control. - Train Multiple Agents for Path Following Control
Train a DQN and a DDPG agent to collaboratively perform adaptive cruise control and lane keeping assist to follow a path. - Train Hybrid SAC Agent for Path-Following Control
Train a hybrid SAC agent for lane following control. - Train Hybrid-Action PPO Agent for Path-Following Control
Train a hybrid PPO agent for lane following control. - Train PPO Agent for Automatic Parking Valet
Train a discrete action space PPO agent to park a car in an open parking space. - Train Reinforcement Learning Agent for Simple Contextual Bandit Problem
Train Q and DQN agents to solve a contextual bandit problem. - Why Solving Regression Using Reinforcement Learning is Not Recommended
Using a reinforcement learning agent to solve a regression problem is possible but not recommended. - Why Solving Classification Using Reinforcement Learning Is Not Recommended
Using a reinforcement learning agent to solve a classification problem is possible but not recommended. - Train Agent to Play Turn-Based Game
Train a DQN agent to play a turn-based game. - Deep Reinforcement Learning for Optimal Trade Execution
This example shows how to use the Reinforcement Learning Toolbox™ and Deep Learning Toolbox™ to design agents for optimal trade execution. - Multiperiod Goal-Based Wealth Management Using Reinforcement Learning
This example shows a reinforcement learning (RL) approach to maximize the probability of obtaining an investor's wealth goal at the end of the investment horizon. - Train DQN Agent for Beam Selection (5G Toolbox)
Train a deep Q-network (DQN) reinforcement learning agent for beam selection in a 5G new radio communications system. (Since R2022b) - Water Distribution System Scheduling Using Reinforcement Learning
Train a DQN agent to optimally activate pumps in a water distribution system.
Train Agents to Perform Control Tasks
Train Agents to Control Robots
Generate Rewards from Control Specifications
Imitation Learning
Train Agents for Automotive Applications
Contextual Bandit Problems
Other Applications
Featured Examples
Identify Vulnerabilities in DC Microgrids
Train a TD3 agent to attack a cyber-physical system to identify vulnerabilities.
Optimizing Queue Selection Strategies Using Reinforcement Learning
Train a DQN agent to optimally route customers through a multi-queue checkout system.
Automatic Parking Valet with Unreal Engine Simulation
Use a TD3 agent with an MPC controller to perform a parking maneuver.
Quadruped Robot Locomotion Using DDPG Agent
Train a DDPG agent to control a quadruped walking robot modeled in Simscape Multibody.
