POPGym: Benchmarking Partially Observable Reinforcement Learning

TL;DR

POPGym introduces a diverse, efficient benchmark suite for partially observable reinforcement learning, enabling comprehensive evaluation of memory models across multiple environments and difficulties.

Contribution

It provides the first large-scale, diverse benchmark with multiple environments and memory baselines, integrated into RLlib for easy use and comparison.

Findings

Largest comparison of RL memory models to date

Environments are diverse, computationally efficient, and converge quickly

Supports plug-and-play integration with various RL algorithms

Abstract

Real world applications of Reinforcement Learning (RL) are often partially observable, thus requiring memory. Despite this, partial observability is still largely ignored by contemporary RL benchmarks and libraries. We introduce Partially Observable Process Gym (POPGym), a two-part library containing (1) a diverse collection of 15 partially observable environments, each with multiple difficulties and (2) implementations of 13 memory model baselines -- the most in a single RL library. Existing partially observable benchmarks tend to fixate on 3D visual navigation, which is computationally expensive and only one type of POMDP. In contrast, POPGym environments are diverse, produce smaller observations, use less memory, and often converge within two hours of training on a consumer-grade GPU. We implement our high-level memory API and memory baselines on top of the popular RLlib framework, providing plug-and-play compatibility with various training algorithms, exploration strategies, and distributed training paradigms. Using POPGym, we execute the largest comparison across RL memory models to date. POPGym is available at https://github.com/proroklab/popgym.