Escape Room: A Configurable Testbed for Hierarchical Reinforcement Learning

TL;DR

The paper introduces the Escape Room Domain (ERD), a new flexible and scalable benchmark for Hierarchical Reinforcement Learning that addresses the limitations of existing testbeds by providing moderate complexity challenges.

Contribution

It presents ERD as a new open-source testbed that bridges the gap between simple and complex HRL environments, facilitating better evaluation and development of HRL algorithms.

Findings

ERD offers scalable difficulty levels for HRL testing.

ERD is compatible with existing RL frameworks and interfaces.

ERD fills the gap between simple and complex HRL benchmarks.

Abstract

Recent successes in Reinforcement Learning have encouraged a fast-growing network of RL researchers and a number of breakthroughs in RL research. As the RL community and the body of RL work grows, so does the need for widely applicable benchmarks that can fairly and effectively evaluate a variety of RL algorithms. This need is particularly apparent in the realm of Hierarchical Reinforcement Learning (HRL). While many existing test domains may exhibit hierarchical action or state structures, modern RL algorithms still exhibit great difficulty in solving domains that necessitate hierarchical modeling and action planning, even when such domains are seemingly trivial. These difficulties highlight both the need for more focus on HRL algorithms themselves, and the need for new testbeds that will encourage and validate HRL research. Existing HRL testbeds exhibit a Goldilocks problem; they are often either too simple (e.g. Taxi) or too complex (e.g. Montezuma's Revenge from the Arcade Learning Environment). In this paper we present the Escape Room Domain (ERD), a new flexible, scalable, and fully implemented testing domain for HRL that bridges the "moderate complexity" gap left behind by existing alternatives. ERD is open-source and freely available through GitHub, and conforms to widely-used public testing interfaces for simple integration and testing with a variety of public RL agent implementations. We show that the ERD presents a suite of challenges with scalable difficulty to provide a smooth learning gradient from Taxi to the Arcade Learning Environment.