Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

TL;DR

Alchemy introduces a complex, procedurally generated 3D benchmark for meta-reinforcement learning, enabling detailed analysis of agent capabilities and limitations in structured, dynamic environments.

Contribution

The paper presents Alchemy, a novel, richly structured 3D benchmark for meta-RL, along with analysis tools and initial agent evaluations.

Findings

Meta-learning agents exhibit specific failures on Alchemy

Alchemy provides a challenging environment for meta-RL research

Tools and sample trajectories are released publicly

Abstract

There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning. One problem in this area of research, however, has been a scarcity of adequate benchmark tasks. In general, the structure underlying past benchmarks has either been too simple to be inherently interesting, or too ill-defined to support principled analysis. In the present work, we introduce a new benchmark for meta-RL research, emphasizing transparency and potential for in-depth analysis as well as structural richness. Alchemy is a 3D video game, implemented in Unity, which involves a latent causal structure that is resampled procedurally from episode to episode, affording structure learning, online inference, hypothesis testing and action sequencing based on abstract domain knowledge. We evaluate a pair of powerful RL agents on Alchemy and present an in-depth analysis of one of these agents. Results clearly indicate a frank and specific failure of meta-learning, providing validation for Alchemy as a challenging benchmark for meta-RL. Concurrent with this report, we are releasing Alchemy as public resource, together with a suite of analysis tools and sample agent trajectories.