We support different padding strategies and alphabet sizes, but by default we choose an alphabet size of 96, where the last character is used for padding.

But at others, the game's two genres feel dissonant. One of the biggest hiccups is being able to unlock dates by grinding (the tedious kind, not the sexual) in the dungeons. Everybody playing this game will have different preferences and may not decide to date all seven characters, but for the purposes of this review, I dated all seven and maxed out all their love ranks. Doing so, I found that I ran out of dungeon levels to play before I could fully level up every character's love rank. So I had to go back and replay dungeon levels.

Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both. Here, we present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based roguelike game, NetHack. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL, while dramatically reducing the computational resources required to gather a large amount of experience. We compare NLE and its task suite to existing alternatives, and discuss why it is an ideal medium for testing the robustness and systematic generalization of RL agents. We demonstrate empirical success for early stages of the game using a distributed Deep RL baseline and Random Network Distillation exploration, alongside qualitative analysis of various agents trained in the environment. NLE is open source at https://github.com/facebookresearch/nle.