Reinforcement Learning MATLAB Toolbox
Type of machine learning that trains an ‘agent’ through trial & error interactions with an environment
How does reinforcement learning training work?
How do I set up and solve a
reinforcement learning problem?
Reinforcement learning toolbox Introduced in MATLAB R2019a
Features
- Built-in and custom Reinforcement Learning Algorithms
- Environment modeling in MATLAB
and Simulink
- Existing Scripts and model can be used
- Deep Learning Toolbox support for representing policies
- Training acceleration with Parallel Computing Toolbox and MATLAB Parallel Servers
- Deployment of trained Policies Reference Examples to get started
MATLAB Toolbox GUI
Reinforcement Learning Designer App
(Introduced in MATLAB R2021a)
How to Open App:
- MATLAB Toolstrip: On the Apps tab, under Machine Learning and Deep Learning, click the app icon.
- MATLAB command prompt: Enter reinforcement Learning Designer.
Using this app, you can:
- Import an existing environment from the MATLAB® workspace or create a predefined environment. Automatically create or import an agent for your environment (DQN, DDPG, TD3, SAC, and PPO agents are supported).
- Train and simulate the agent
- against the environment. Analyze simulation results and refine your agent parameters. Export the final agent to the
- MATLAB workspace for further use and deployment.
Comments
Post a Comment