Papers › Distributional Bellman Operators over Mean Embeddings

Distributional Bellman Operators over Mean Embeddings

9 Dec 2023arXiv:2312.07358archive 2025-07-28

Li Kevin Wenliang, Grégoire Delétang, Matthew Aitchison, Marcus Hutter, Anian Ruoss, Arthur Gretton, Mark Rowland

We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several new algorithms for dynamic programming and temporal-difference learning based on this framework, provide asymptotic convergence theory, and examine the empirical performance of the algorithms on a suite of tabular tasks. Further, we show that this approach can be straightforwardly combined with deep reinforcement learning, and obtain a new deep RL agent that improves over baseline distributional approaches on the Arcade Learning Environment.

Paper PDF Code

Code

google-deepmind/sketch_dqn officialmentioned in papermentioned on GitHubjax 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

Atari Games Deep Reinforcement Learning Distributional Reinforcement Learning Reinforcement Learning reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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