好奇心駆動学習の大規模研究
Large-Scale Study of Curiosity-Driven Learning
外発的報酬なしに予測誤差を報酬とする好奇心のみで54のベンチマーク環境を学習し、多くのゲームで良好に機能することを示した大規模研究。
著者: Yuri Burda, Harri Edwards, Deepak Pathak, Amos Storkey, Trevor Darrell, Alexei A. Efros
分類: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML
原文アブストラクト
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our results show surprisingly good performance, and a high degree of alignment between the intrinsic curiosity objective and the hand-designed extrinsic rewards of many game environments. (b) We investigate the effect of using different feature spaces for computing prediction error and show that random features are sufficient for many popular RL game benchmarks, but learned features appear to generalize better (e.g. to novel game levels in Super Mario Bros.). (c) We demonstrate limitations of the prediction-based rewards in stochastic setups. Game-play videos and code are at https://pathak22.github.io/large-scale-curiosity/
