KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Becker, Philipp, Freymuth, Niklas, Neumann, Gerhard
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929394237308928
author Becker, Philipp
Freymuth, Niklas
Neumann, Gerhard
author_facet Becker, Philipp
Freymuth, Niklas
Neumann, Gerhard
contents Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their recent deterministic counterparts such as S4 or Mamba. We propose KalMamba, an efficient architecture to learn representations for RL that combines the strengths of probabilistic SSMs with the scalability of deterministic SSMs. KalMamba leverages Mamba to learn the dynamics parameters of a linear Gaussian SSM in a latent space. Inference in this latent space amounts to standard Kalman filtering and smoothing. We realize these operations using parallel associative scanning, similar to Mamba, to obtain a principled, highly efficient, and scalable probabilistic SSM. Our experiments show that KalMamba competes with state-of-the-art SSM approaches in RL while significantly improving computational efficiency, especially on longer interaction sequences.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15131
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty
Becker, Philipp
Freymuth, Niklas
Neumann, Gerhard
Machine Learning
Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their recent deterministic counterparts such as S4 or Mamba. We propose KalMamba, an efficient architecture to learn representations for RL that combines the strengths of probabilistic SSMs with the scalability of deterministic SSMs. KalMamba leverages Mamba to learn the dynamics parameters of a linear Gaussian SSM in a latent space. Inference in this latent space amounts to standard Kalman filtering and smoothing. We realize these operations using parallel associative scanning, similar to Mamba, to obtain a principled, highly efficient, and scalable probabilistic SSM. Our experiments show that KalMamba competes with state-of-the-art SSM approaches in RL while significantly improving computational efficiency, especially on longer interaction sequences.
title KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty
topic Machine Learning
url https://arxiv.org/abs/2406.15131