DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software.

DeepMind Lab provides a suite of challenging 3D navigation and puzzle-solving tasks for learning agents. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.

Disclaimer: This is not an official Google product.

If you use DeepMind Lab in your research and would like to cite the DeepMind Lab environment, we suggest you cite the DeepMind Lab paper.

You can reach us at [email protected].

• Get Bazel from bazel.io.

• Clone DeepMind Lab, e.g. by running

$ git clone https://github.com/deepmind/lab
$ cd lab

• For a live example of a random agent, run

lab$ bazel run :random_agent --define headless=false -- \
               --length=10000 --width=640 --height=480

Here is some more detailed build documentation, including how to install dependencies if you don't have them.

To test the game using human input controls, run

lab$ bazel run :game -- --level_script tests/demo_map

DeepMind Lab ships with an example random agent in python/random_agent.py which can be used as a starting point for implementing a learning agent. To let this agent interact with DeepMind Lab for training, run

lab$ bazel run :random_agent

The Python API for the agent-environment interaction is described in docs/python_api.md.

DeepMind Lab ships with different levels implementing different tasks. These tasks can be configured using Lua scripts, as described in docs/lua_api.md.

DeepMind Lab is built from the ioquake3 game engine, and it uses the tools q3map2 and bspc for map creation. Bug fixes and cleanups that originate with those projects are best fixed upstream and then merged into DeepMind Lab.

• bspc is taken from github.com/TTimo/bspc, revision e6f90a2dc02916aa2298da6ace70a8333b3f2405. There are virtually no local modifications, although we integrate this code with the main ioq3 code and do not use their copy in the deps directory. We expect this code to be stable.

• q3map2 is taken from github.com/TTimo/GtkRadiant, revision 8557f1820f8e0c7cef9d52a78b2847fa401a4a95. A few minor local modifications add synchronization and use C99 constructs to replace formerly non-portable or undefined behaviour. We also expect this code to be stable.

• ioquake3 is taken from github.com/ioquake/ioq3, revision 1c1e1f61f180596c925a4ac0eddba4806d1369cd. The code contains extensive modifications and additions. We aim to merge upstream changes occasionally.

We are very grateful to the maintainers of these repositories for all their hard work on maintaining high-quality code bases.

DeepMind Lab currently ships as source code only. It depends on a few external software libraries, which we ship in several different ways:

• The zlib, glib, libxml2, jpeg and png libraries are referenced as external Bazel sources, and Bazel BUILD files are provided. The dependent code itself should be fairly portable, but the BUILD rules we ship are specific to Linux on x86. To build on a different platform you will most likely have to edit those BUILD files.

• Message digest algorithms are included in this package (in //third_party/md), taken from the reference implementations of their respective RFCs. A "generic reinforcement learning API" is included in //third_party/rl_api, which has also been created by the DeepMind Lab authors. This code is portable.

• Several additional libraries are required but are not shipped in any form; they must be present on your system:

  • SDL 2
  • Lua 5.1 (later versions might work, too)
  • gettext (required by glib)
  • OpenGL: a hardware driver and library are needed for hardware-accelerated human play, and OSMesa is required for the software-rendering, headless library that machine learning agents will want to use.
  • Python 2.7 (other versions might work, too)

The build rules are using a few compiler settings that are specific to GCC. If some flags are not recognized by your compiler (typically those would be specific warning suppressions), you may have to edit those flags. The warnings should be noisy but harmless.