Deep Reinforcement Learning In Action

Code Snippets from the Deep Reinforcement Learning in Action book from Manning, Inc

How this is Organized

The code snippets, listings, and projects are all embedded in Jupyter Notebooks organized by chapter. Visit http://jupyter.org/install for instructions on installing Jupyter Notebooks.

The chapter directories contain the maintained notebooks. See Book compatibility and corrections for API updates and corrections to printed listings, and Errata for links to maintained chapters and the immutable pre-refresh source. Model architectures and the methods described in the text are preserved; stochastic learning results vary between runs.

Requirements

In order to run many of the projects, you'll need at least the NumPy library and PyTorch.

python -m pip install -r requirements.txt

Use a fresh Python 3.13 environment and launch each notebook from its chapter directory. Run python -m unittest discover -s tests -v for the fast checks. See validation results for full training outcomes and tested limits.

Contribute

If you experience any issues running the examples, please file an issue. If you see typos or other errors in the book, please edit the Errata.md file and create a pull request.

Automated tests

See TESTING.md for PR regression/smoke checks, weekly and manual full-training runs, local commands, and merge-protection setup.