From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Wanjari, Sarthak
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915799365582848
author Wanjari, Sarthak
author_facet Wanjari, Sarthak
contents Offline Reinforcement Learning (RL) promises the recovery of optimal policies from static datasets, yet it remains susceptible to the overestimation of out-of-distribution (OOD) actions, particularly in fractured and sparse data manifolds. Current solutions necessitate a trade-off between computational efficiency and performance. Methods like CQL offer rigorous conservatism but require tremendous compute power while efficient expectile-based methods like IQL often fail to correct OOD errors on pathological datasets, collapsing to Behavioural Cloning. In this work, we propose Geometric Pessimism, a modular, compute-efficient framework that augments standard IQL with density-based penalty derived from k-nearest-neighbour distances in the state-action embedding space. By pre-computing the penalties applied to each state-action pair, our method injects OOD conservatism via reward shaping with a O(1) training overhead to the training loop. Evaluated on the D4RL MuJoCo benchmark, our method, Geo-IQL outperforms standard IQL on sensitive and unstable medium-replay tasks by over 18 points, while reducing inter-seed standard-deviation by 4 times. Furthermore, Geo-IQL does not degrade performance on stable manifolds. Crucially, we validate our algorithm on the MIMIC-III Sepsis critical care dataset. While standard IQL collapses to behaviour cloning, Geo-IQL demonstrates active policy improvement. Maintaining safety constraints, it achieves 86.4% terminal agreement with clinicians compared to IQL's 75%. Our results suggest that geometric pessimism provides the necessary regularisation to safely overcome local optima in critical, real-world decision systems.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08655
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism
Wanjari, Sarthak
Machine Learning
Offline Reinforcement Learning (RL) promises the recovery of optimal policies from static datasets, yet it remains susceptible to the overestimation of out-of-distribution (OOD) actions, particularly in fractured and sparse data manifolds. Current solutions necessitate a trade-off between computational efficiency and performance. Methods like CQL offer rigorous conservatism but require tremendous compute power while efficient expectile-based methods like IQL often fail to correct OOD errors on pathological datasets, collapsing to Behavioural Cloning. In this work, we propose Geometric Pessimism, a modular, compute-efficient framework that augments standard IQL with density-based penalty derived from k-nearest-neighbour distances in the state-action embedding space. By pre-computing the penalties applied to each state-action pair, our method injects OOD conservatism via reward shaping with a O(1) training overhead to the training loop. Evaluated on the D4RL MuJoCo benchmark, our method, Geo-IQL outperforms standard IQL on sensitive and unstable medium-replay tasks by over 18 points, while reducing inter-seed standard-deviation by 4 times. Furthermore, Geo-IQL does not degrade performance on stable manifolds. Crucially, we validate our algorithm on the MIMIC-III Sepsis critical care dataset. While standard IQL collapses to behaviour cloning, Geo-IQL demonstrates active policy improvement. Maintaining safety constraints, it achieves 86.4% terminal agreement with clinicians compared to IQL's 75%. Our results suggest that geometric pessimism provides the necessary regularisation to safely overcome local optima in critical, real-world decision systems.
title From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism
topic Machine Learning
url https://arxiv.org/abs/2602.08655