堅牢でドメイン非依存な強化学習コンペティション設計へ向けて
Towards robust and domain agnostic reinforcement learning competitions
再学習・ドメインランダム化・ドメイン難読化・計算資源制限の4機構で、再現性が高く汎用的でサンプル効率の良いアルゴリズムを促すコンペ設計を提案し、MineRL 2020で実証した。
著者: William Hebgen Guss, Stephanie Milani, Nicholay Topin, Brandon Houghton, Sharada Mohanty, Andrew Melnik, Augustin Harter, Benoit Buschmaas, Bjarne Jaster, Christoph Berganski, Dennis Heitkamp, Marko Henning, Helge Ritter, Chengjie Wu, Xiaotian Hao, Yiming Lu, Hangyu Mao, Yihuan Mao, Chao Wang, Michal Opanowicz, Anssi Kanervisto, Yanick Schraner, Christian Scheller, Xiren Zhou, Lu Liu, Daichi Nishio, Toi Tsuneda, Karolis Ramanauskas, Gabija Juceviciute
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
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.
