NetHack Learning Environment (NLE)
A procedurally-generated grid-world dungeon-crawl game that strikes a great balance between complexity and speed for single-agent RL research.
reinforcement-learning game nethack gym library research article code

The NetHack Learning Environment is a novel research environment for testing the robustness and systematic generalization of reinforcement learning (RL) agents. The environment is based on NetHack , one of the oldest and most popular procedurally generated roguelike games. Existing RL environments are either sufficiently complex or based on fast simulation, but they are rarely both. In contrast, the NetHack Learning Environment combines lightning-fast simulation with very complex game dynamics that are difficult even for humans to master. This allows our agents to experience billions of steps in the environment in a reasonable time frame while still challenging the limits of what current methods can achieve, driving long-term research on topics such as exploration, planning, skill acquisition, and language-conditioned RL.

Don't forget to tag @heiner , @rockt in your comment, otherwise they may not be notified.

Authors community post
At various times a mathematician, technical consultant at @google, and research engineer at @deepmind and @facebookresearch.
Research Scientist at Facebook AI Research and Lecturer at UCL. Working on Deep & Reinforcement Learning and NLP.
Share this project
Similar projects
Reinforcement Learning Tutorial
Important reinforcement learning (RL) algorithms, including policy iteration, Q-Learning, and Neural Fitted Q.
Deep Model-Based RL for Real-World Robotic Control
Short talk about model-based RL by Sergey Levine.
Plan2Explore: Plan to Explore via Self-Supervised World Models
A self-supervised reinforcement learning agent that tackles task-specific and the sample efficiency challenges.
Rlx: A modular Deep RL library for research
"rlx" is a Deep RL library written on top of PyTorch & built for educational and research purpose.