Papers › The Effectiveness of World Models for Continual Reinforcement Learning

The Effectiveness of World Models for Continual Reinforcement Learning

29 Nov 2022arXiv:2211.15944archive 2025-07-28

Samuel Kessler, Mateusz Ostaszewski, Michał Bortkiewicz, Mateusz Żarski, Maciej Wołczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr Miłoś

World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically employ a replay buffer for training, which can be naturally extended to continual learning. We systematically study how different selective experience replay methods affect performance, forgetting, and transfer. We also provide recommendations regarding various modeling options for using world models. The best set of choices is called Continual-Dreamer, it is task-agnostic and utilizes the world model for continual exploration. Continual-Dreamer is sample efficient and outperforms state-of-the-art task-agnostic continual reinforcement learning methods on Minigrid and Minihack benchmarks.

PaperPDFCode

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

Code

skezle/continual-dreamer officialmentioned in papermentioned on GitHubtf report
facebookresearch/minihack mentioned on GitHubpytorchApache-2.0 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

Continual LearningModel-based Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

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