Papers › Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning

Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning

19 Mar 2024arXiv:2403.12856archive 2025-07-28

Mirco Theile, Hongpeng Cao, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli

In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant to exploit these symmetries is a substantial challenge. Related works try to design networks that are equivariant and invariant by construction, limiting them to a very restricted library of components, which in turn hampers the expressiveness of the networks. This paper proposes a method to construct equivariant policies and invariant value functions without specialized neural network components, which we term equivariant ensembles. We further add a regularization term for adding inductive bias during training. In a map-based path planning case study, we show how equivariant ensembles and regularization benefit sample efficiency and performance.

PaperPDFCode

Code

theilem/uavSim officialmentioned in papermentioned on GitHubtfBSD-3-Clause 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

Inductive BiasReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PPO

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