Large-scale study of curiosity-driven learning

Large-scale study of curiosity-driven learning | OpenAI

August 13, 2018

Publication

Large-scale study of curiosity-driven learning

Read paper

Loading…

Share

Abstract

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 this https URL⁠.

• Learning Paradigms

Authors

Yura Burda, Harri Edwards, Deepak Pathak, Amos Storkey, Trevor Darrell, Alexei A. Efros

Related articles

View all

Scaling laws for reward model overoptimizationPublicationOct 19, 2022

Learning to play Minecraft with Video PreTrainingConclusionJun 23, 2022

Dota 2 with large scale deep reinforcement learningPublicationDec 13, 2019