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.

For more information about NetHack, check out its wikipedia article,, and NetHack wiki.

NetHack Learning Environment

The NetHack Learning Environment (NLE) is a Reinforcement Learning environment based on NetHack 3.6.6 and designed to provide a standard RL interface to the game, and comes You can read more about NLE in the NeurIPS 2020 paper.

Example of an agent running on NLE