Benchmark Examples
Compare default reinforcement learning agents on predefined environments
Different types of reinforcement learning agents have a diverse, and typically complementary, set of strengths and weaknesses. Compare the performance of different agents over a range of benchmark problems.
Tutorials
- Compare Agents on Basic Grid World
Compare discrete action space agents on the basic grid world environment. - Compare Agents on Deterministic Waterfall Grid World
Compare discrete action space agents on the deterministic waterfall grid world environment. - Compare Agents on Stochastic Waterfall Grid World
Compare discrete action space agents on the stochastic waterfall grid world environment. - Compare Agents on Discrete Double-Integrator
Compare default agents on the MATLAB® discrete action space double-integrator environment. - Compare Agents on Discrete Cart-Pole
Compare default agents on the MATLAB discrete action space cart-pole environment. - Compare Agents on the Discrete Pendulum Swing-Up
Compare default agents on the Simulink® discrete action space simple pendulum swing-up environment. - Compare Agents on Discrete Simscape Cart-Pole Swing-Up
Compare default agents on the Simscape™ Multibody™ discrete action space cart-pole swing-up environment. - Compare Agents on Discrete Pendulum Swing-Up with Image
Compare default agents on the MATLAB discrete action space pendulum swing-up with image environment. - Compare Agents on Continuous Double-Integrator
Compare default agents on the MATLAB continuous action space double-integrator environment. - Compare Agents on Continuous Cart Pole
Compare default agents on the MATLAB continuous action space cart-pole environment. - Compare Agents on Continuous Pendulum Swing-Up
Compare default agents on the Simulink continuous action space simple pendulum swing-up environment. - Compare Agents on Continuous Cart Pole Swing-Up
Compare default agents on the Simscape Multibody continuous action space cart-pole swing-up environment. - Compare Agents on Continuous Pendulum Swing-Up with Image
Compare default agents on the MATLAB continuous action space simple pendulum swing-up with image environment.
Compare Agents on Grid World Environments
Compare Agents on Predefined Discrete Control System Environments
Compare Agents on Predefined Continuous Control System Environments
Featured Examples
Compare DDPG Agent to LQR Controller
Train a DDPG agent with custom approximator to control a second-order dynamic system modeled in MATLAB and compare it to an LQR controller.
