Papers › Curious Replay for Model-based Adaptation

Curious Replay for Model-based Adaptation

28 Jun 2023arXiv:2306.15934archive 2025-07-28

Isaac Kauvar, Chris Doyle, Linqi Zhou, Nick Haber

Agents must be able to adapt quickly as an environment changes. We find that existing model-based reinforcement learning agents are unable to do this well, in part because of how they use past experiences to train their world model. Here, we present Curious Replay -- a form of prioritized experience replay tailored to model-based agents through use of a curiosity-based priority signal. Agents using Curious Replay exhibit improved performance in an exploration paradigm inspired by animal behavior and on the Crafter benchmark. DreamerV3 with Curious Replay surpasses state-of-the-art performance on Crafter, achieving a mean score of 19.4 that substantially improves on the previous high score of 14.5 by DreamerV3 with uniform replay, while also maintaining similar performance on the Deepmind Control Suite. Code for Curious Replay is available at https://github.com/AutonomousAgentsLab/curiousreplay

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

autonomousagentslab/curiousreplay officialmentioned in papermentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Model-based Reinforcement Learningmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Experience ReplayPrioritized Experience Replay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections