Towards robust and domain agnostic reinforcement learning competitions
This addresses the issue of biased and non-reproducible algorithms in RL competitions for researchers and practitioners, representing an incremental improvement in competition design.
The paper tackles the problems of domain-specific, compute-biased, and non-reproducible solutions in reinforcement learning competitions by proposing a new competition design framework with four mechanisms, and demonstrates its efficacy through the MineRL 2020 Competition, resulting in submissions that are reproducible, domain-agnostic, and sample/resource efficient.
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Despite this, a majority of challenges suffer from the same fundamental problems: participant solutions to the posed challenge are usually domain-specific, biased to maximally exploit compute resources, and not guaranteed to be reproducible. In this paper, we present a new framework of competition design that promotes the development of algorithms that overcome these barriers. We propose four central mechanisms for achieving this end: submission retraining, domain randomization, desemantization through domain obfuscation, and the limitation of competition compute and environment-sample budget. To demonstrate the efficacy of this design, we proposed, organized, and ran the MineRL 2020 Competition on Sample-Efficient Reinforcement Learning. In this work, we describe the organizational outcomes of the competition and show that the resulting participant submissions are reproducible, non-specific to the competition environment, and sample/resource efficient, despite the difficult competition task.