This paper argues that the current main approaches in multi-objective RL (SER and ESR), and successor features, are insufficient, and motivates that this can indeed be the case by an example, leading to a new perspective, and a significant and non-trivial gap in the literature.
Abstract
Time is of the essence when dealing with multiple reward signals and non-linear utility. In this paper we argue that the current main approaches in multi-objective RL (SER and ESR), and successor features, are insufficient. While each approach deals with non-linear effects on user utility on different timescales, none of them take into account that different effects happening on different timescales can happen within the same decision problem. We motivate that this can indeed be the case by an example, both intuitively and numerically, leading to a new perspective, and a significant and non-trivial gap in the literature.
This paper overviews the paths to further improve this algorithm and identifies two major methods of improvement: the internal method focuses on changing the inner structure of the algorithm to make it more generalizable in various circumstances; the external method focuses on constructing multi-phase processes with MA...
Heng-Nian Pan· Proceedings of the 4th Inter...· 0 citations
The orienteering problem (OP) and its many variants are standard models for route planning when rewards are uncertain. Almost all of these models share one assumption: the reward at a location is either fixed or changes on its own, independently of what the traveller does. This paper studies a different setting. Visiti...
Advaith Jyothi Arun· Princeton Journal of Pre-Col...· 0 citations
RLTL;DR is introduced, a promising compacted training paradigm of the form"on this sort of task, keep this sort of thing in mind", which it is hoped will inspire future research on.
Michael Kirchhof, Eleonora Gualdoni, Andrew Szot et al.· 1 citation
A bound on Generalized Policy Improvement (GPI) is derived that explicitly quantifies how performance degrades with the mismatch between transition kernels, recovering existing successor-feature guarantees when dynamics are shared.
Erik Nikulski, Yamen Habib, Vicenç Gómez et al.· 0 citations
This work introduces Steiner's taxonomy of group tasks as a framework for analyzing multi-agent LLM scaling and shows that task structure is a fundamental determinant of team scaling.
Many reinforcement-learning (RL) problems are non-stationary yet structured and can be decomposed into phases, each with its own transition probabilities and reward functions. When the phase sequence is known, the common solution augments the state with information to satisfy the Markovian property and applies standard...
Guilhem Loussouarn, Nancy Nayak, Kin K. Leung· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
