MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
This provides a versatile platform for researchers in reinforcement learning to create custom testbeds, though it is incremental as it builds on existing game dynamics.
The authors tackled the lack of flexible benchmarks for evaluating specific capabilities in reinforcement learning by introducing MiniHack, a sandbox framework that enables easy design of novel RL environments using NetHack's rich dynamics, resulting in a tool that supports tasks from small rooms to complex procedurally generated worlds.
Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that are widely adopted by the community are not explicitly designed for evaluating specific capabilities of RL methods. While there exist environments for assessing particular open problems in RL (such as exploration, transfer learning, unsupervised environment design, or even language-assisted RL), it is generally difficult to extend these to richer, more complex environments once research goes beyond proof-of-concept results. We present MiniHack, a powerful sandbox framework for easily designing novel RL environments. MiniHack is a one-stop shop for RL experiments with environments ranging from small rooms to complex, procedurally generated worlds. By leveraging the full set of entities and environment dynamics from NetHack, one of the richest grid-based video games, MiniHack allows designing custom RL testbeds that are fast and convenient to use. With this sandbox framework, novel environments can be designed easily, either using a human-readable description language or a simple Python interface. In addition to a variety of RL tasks and baselines, MiniHack can wrap existing RL benchmarks and provide ways to seamlessly add additional complexity.