The NetHack Learning Environment





GitHub Stars



Last Commit

3d ago







NetHack General Public License



NetHack Learning Environment (NLE)

CircleCI GitHub PyPI version Downloads

The NetHack Learning Environment (NLE) is a Reinforcement Learning environment presented at NeurIPS 2020. NLE is based on NetHack 3.6.6 and designed to provide a standard RL interface to the game, and comes with tasks that function as a first step to evaluate agents on this new environment.

NetHack is one of the oldest and arguably most impactful videogames in history, as well as being one of the hardest roguelikes currently being played by humans. It is procedurally generated, rich in entities and dynamics, and overall an extremely challenging environment for current state-of-the-art RL agents, while being much cheaper to run compared to other challenging testbeds. Through NLE, we wish to establish NetHack as one of the next challenges for research in decision making and machine learning.

You can read more about NLE in the NeurIPS 2020 paper, and about NetHack in its original README, at, and on the NetHack wiki.

Example of an agent running on NLE

Papers using the NetHack Learning Environment

Open a pull request to add papers.

Getting started

Starting with NLE environments is extremely simple, provided one is familiar with other gym / RL environments.


NLE requires python>=3.5, cmake>=3.15 to be installed and available both when building the package, and at runtime.

On MacOS, one can use Homebrew as follows:

$ brew install cmake

On a plain Ubuntu 18.04 distribution, cmake and other dependencies can be installed by doing:

# Python and most build deps
$ sudo apt-get install -y build-essential autoconf libtool pkg-config \
    python3-dev python3-pip python3-numpy git flex bison libbz2-dev

# recent cmake version
$ wget -O - 2>/dev/null | sudo apt-key add -
$ sudo apt-add-repository 'deb bionic main'
$ sudo apt-get update && apt-get --allow-unauthenticated install -y \
    cmake \

Afterwards it's a matter of setting up your environment. We advise using a conda environment for this:

$ conda create -n nle python=3.8
$ conda activate nle
$ pip install nle

NOTE: If you want to extend / develop NLE, please install the package as follows:

$ git clone --recursive
$ pip install -e ".[dev]"
$ pre-commit install


We have provided some docker images. Please see the relevant README.

Trying it out

After installation, one can try out any of the provided tasks as follows:

>>> import gym
>>> import nle
>>> env = gym.make("NetHackScore-v0")
>>> env.reset()  # each reset generates a new dungeon
>>> env.step(1)  # move agent '@' north
>>> env.render()

NLE also comes with a few scripts that allow to get some environment rollouts, and play with the action space:

# Play NetHackStaircase-v0 as a human
$ python -m

# Use a random agent
$ python -m --mode random

# Play the full game using directly the NetHack internal interface
# (Useful for debugging outside of the gym environment)
$ python -m --env NetHackScore-v0 # works with random agent too

# See all the options
$ python -m --help

Note that can also be run with nle-play, if the package has been properly installed.

Additionally, a TorchBeast agent is bundled in nle.agent together with a simple model to provide a starting point for experiments:

$ pip install "nle[agent]"
$ python -m nle.agent.agent --num_actors 80 --batch_size 32 --unroll_length 80 --learning_rate 0.0001 --entropy_cost 0.0001 --use_lstm --total_steps 1000000000

Plot the mean return over the last 100 episodes:

$ python -m nle.scripts.plot
                              averaged episode return

  140 +---------------------------------------------------------------------+
      |             +             +            ++-+ ++++++++++++++++++++++++|
      |             :             :          ++++++++||||||||||||||||||||||||
  120 |-+...........:.............:...+-+.++++|||||||||||||||||||||||||||||||
      |             :        +++++++++++++++||||||||||AAAAAAAAAAAAAAAAAAAAAA|
      |            +++++++++++++||||||||||||||AAAAAAAAAAAA|||||||||||||||||||
  100 |-+......+++++|+|||||||||||||||||||||||AA||||||||||||||||||||||||||||||
      |       +++|||||||||||||||AAAAAAAAAAAAAA|||||||||||+++++++++++++++++++|
      |    ++++|||||AAAAAAAAAAAAAA||||||||||||++++++++++++++-+:             |
   80 |-++++|||||AAAAAA|||||||||||||||||||||+++++-+...........:...........+-|
      | ++|||||AAA|||||||||||||||++++++++++++-+ :             :             |
   60 |++||AAAAA|||||+++++++++++++-+............:.............:...........+-|
      |++|AA||||++++++-|-+        :             :             :             |
      |+|AA|||+++-+ :             :             :             :             |
   40 |+|A+++++-+...:.............:.............:.............:...........+-|
      |+AA+-+       :             :             :             :             |
      |AA-+         :             :             :             :             |
   20 |AA-+.........:.............:.............:.............:...........+-|
      |++-+         :             :             :             :             |
      |+-+          :             :             :             :             |
    0 |-+...........:.............:.............:.............:...........+-|
      |+            :             :             :             :             |
      |+            +             +             +             +             |
  -20 +---------------------------------------------------------------------+
      0           2e+08         4e+08         6e+08         8e+08         1e+09


We welcome contributions to NLE. If you are interested in contributing please see this document.


NLE is direct fork of NetHack and therefore contains code that operates on many different levels of abstraction. This ranges from low-level game logic, to the higher-level administration of repeated nethack games, and finally to binding of these games to Python gym environment.

If you want to learn more about the architecture of nle and how it works under the hood, checkout the architecture document. This may be a useful starting point for anyone looking to contribute to the lower level elements of NLE.

Related Environments

Interview about the environment with Weights&Biases

Facebook AI Research’s Tim & Heiner on democratizing reinforcement learning research.

Interview with Weigths&Biases


If you use NLE in any of your work, please cite:

  author    = {Heinrich K{\"{u}}ttler and
               Nantas Nardelli and
               Alexander H. Miller and
               Roberta Raileanu and
               Marco Selvatici and
               Edward Grefenstette and
               Tim Rockt{\"{a}}schel},
  title     = {{The NetHack Learning Environment}},
  booktitle = {Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)},
  year      = {2020},

Rate & Review

Great Documentation0
Easy to Use0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Unwelcoming Community0