DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seo, Younggyo | ko |
dc.contributor.author | Chen, Lili | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.contributor.author | Lee, Honglak | ko |
dc.contributor.author | Abbeel, Pieter | ko |
dc.contributor.author | Lee, Kimin | ko |
dc.date.accessioned | 2022-01-14T06:56:15Z | - |
dc.date.available | 2022-01-14T06:56:15Z | - |
dc.date.created | 2021-12-02 | - |
dc.date.created | 2021-12-02 | - |
dc.date.created | 2021-12-02 | - |
dc.date.created | 2021-12-02 | - |
dc.date.issued | 2021-07 | - |
dc.identifier.citation | 38th International Conference on Machine Learning, ICML 2021 | - |
dc.identifier.issn | 2640-3498 | - |
dc.identifier.uri | http://hdl.handle.net/10203/291830 | - |
dc.description.abstract | Recent exploration methods have proven to be a recipe for improving sample-efficiency in deep reinforcement learning (RL). However, efficient exploration in high-dimensional observation spaces still remains a challenge. This paper presents Random Encoders for Efficient Exploration (RE3), an exploration method that utilizes state entropy as an intrinsic reward. In order to estimate state entropy in environments with high-dimensional observations, we utilize a k-nearest neighbor entropy estimator in the low-dimensional representation space of a convolutional encoder. In particular, we find that the state entropy can be estimated in a stable and compute-efficient manner by utilizing a randomly initialized encoder, which is fixed throughout training. Our experiments show that RE3 significantly improves the sample-efficiency of both model-free and model-based RL methods on locomotion and navigation tasks from DeepMind Control Suite and MiniGrid benchmarks. We also show that RE3 allows learning diverse behaviors without extrinsic rewards, effectively improving sample-efficiency in downstream tasks. | - |
dc.language | English | - |
dc.publisher | JMLR-JOURNAL MACHINE LEARNING RESEARCH | - |
dc.title | State Entropy Maximization with Random Encoders for Efficient Exploration | - |
dc.type | Conference | - |
dc.identifier.wosid | 000768182705055 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 38th International Conference on Machine Learning, ICML 2021 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Shin, Jinwoo | - |
dc.contributor.localauthor | Lee, Kimin | - |
dc.contributor.nonIdAuthor | Chen, Lili | - |
dc.contributor.nonIdAuthor | Lee, Honglak | - |
dc.contributor.nonIdAuthor | Abbeel, Pieter | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.