Benchmark Examples

Tutorials

Compare Default Agents on Predefined Discrete Control System Environments

• Compare Agents on the Discrete Double-Integrator Environment
  Compare default agents on the MATLAB^® discrete action space double-integrator environment.
• Compare Agents on the Discrete Cart-Pole Environment
  Compare default agents on the MATLAB discrete action space cart-pole environment.
• Compare Agents on the Discrete Pendulum Swing-Up Environment
  Compare default agents on the Simulink^® discrete action space simple pendulum swing-up environment.
• Compare Agents on the Discrete Simscape Cart-Pole Swing-Up Environment
  Compare default agents on the Simscape™ Multibody™ discrete action space cart-pole swing-up environment.
• Compare Agents on the Discrete Pendulum Swing-Up with Image Environment
  Compare default agents on the MATLAB discrete action space pendulum swing-up with image environment.

Compare Default Agents on Predefined Continuous Control System Environments

• Compare Agents on the Continuous Double Integrator Environment
  Compare default agents on the MATLAB continuous action space double-integrator environment.
• Compare Agents on the Continuous Cart Pole
  Compare default agents on the MATLAB continuous action space cart-pole environment.
• Comparison of Agents on the Continuous Pendulum Swing-Up Environment
  Compare default agents on the Simulink continuous action space simple pendulum swing-up environment.
• Compare Agents on the Continuous Cart Pole Swing-Up Environment
  Compare default agents on the Simscape Multibody continuous action space cart-pole swing-up environment.
• Compare Agents on Continuous Pendulum Swing-Up with Image Environment
  Compare default agents on the MATLAB continuous action space simple pendulum swing-up with image environment.

Train Agents with Custom Networks to Control Double Integrator System

• Train PG Agent with Custom Networks to Control Discrete Double Integrator
  Train a PG agent with a baseline to control a discrete action space double integrator system modeled in MATLAB.

Train Agents to Balance Cart-Pole System

• Train LSPI Agent to Balance Discrete Cart-Pole System
  Train an LSPI agent to balance discrete action space cart-pole system modeled in MATLAB.
• Train DQN Agent to Balance Discrete Cart-Pole System
  Train a DQN agent to balance discrete action space cart-pole system modeled in MATLAB.
• Train PG Agent to Balance Discrete Cart-Pole System
  Train a PG agent to balance a discrete action space cart-pole system modeled in MATLAB.
• Train AC Agent to Balance Discrete Cart-Pole System
  Train an AC agent to balance a discrete action space cart-pole system modeled in MATLAB.
• Train AC Agent to Balance Discrete Cart-Pole System Using Parallel Computing
  Train an AC agent to control a discrete action space cart-pole system using asynchronous parallel computing.
• Train MBPO Agent to Balance Continuous Cart-Pole System
  A model-based reinforcement learning agent learns a model of its environment that it can use to generate additional experiences for training.

Train Agents to Swing Up and Balance Pendulum

• Train DQN Agent to Swing Up and Balance Pendulum
  Train a DQN agent to swing up and balance a discrete action space pendulum modeled in Simulink.
• Train DDPG Agent to Swing Up and Balance Pendulum
  Train a DDPG agent to balance a continuous action space pendulum modeled in Simulink.
• Train DDPG Agent to Swing Up and Balance Pendulum with Bus Signal
  Train a DDPG agent to balance a continuous action space pendulum Simulink model that contains observations in a bus signal.
• Train DDPG Agent to Swing Up and Balance Pendulum with Image Observation
  Train a DDPG agent using an image-based observation signal.
• Create DQN Agent Using Deep Network Designer and Train Using Image Observations
  Create a reinforcement learning agent using the Deep Network Designer app from the Deep Learning Toolbox™.

Train Agents to Swing Up and Balance Cart-Pole System

• Train DDPG Agent to Swing Up and Balance Cart-Pole System
  Train a DDPG agent to swing up and balance a continuous action space cart-pole system modeled in Simscape Multibody.

Train Agents to Land a Flying Vehicle

• Train PPO Agent for a Lander Vehicle
  Train a discrete PPO agent to land a flying vehicle.
• Train Discrete Soft Actor Critic Agent for Lander Vehicle
  Train a discrete SAC agent to land a flying vehicle.

Featured Examples

Compare DDPG Agent to LQR Controller

Train a DDPG agent to control a second-order dynamic system modeled in MATLAB and compare it to an LQR controller.

• Open Live Script

Train MBPO Agent to Balance Continuous Cart-Pole System

A model-based reinforcement learning agent learns a model of its environment that it can use to generate additional experiences for training.

• Open Live Script