Successor Representations

Follow this topic Ask about this topic

Recent momentum

-67%

1 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

14 papers

Latest in Successor Representations

Open your feed →

It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning
Aug 26, 2026Liam P. H. Mertens, Lucas N. Alegre, Florent Delgrange +3Successor Representations Expected Utility
Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning
Aug 12, 2026Zijian Zhao, Sen LiMulti-Agent Reinforcement Learning Successor Representations
ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning
Aug 5, 2026R. Blake Lawlor, Daniel S. BrownModel-Free Reinforcement Learning Successor Representations
Constrained Reinforcement Learning Using Successor Representations
Jul 27, 2026Michael Girstl, Alexander Mattick, Christopher MutschlerConstrained Reinforcement Learning Safety Constraints
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs
May 30, 2026Subhadip MitraSafety Alignment Red-Teaming
The Terminal Representation in Reinforcement Learning
May 29, 2026Amir Esterhuysen, Anders JonssonRepresentation Learning Successor Representations
Balancing Plasticity and Stability with Fast and Slow Successor Features
May 25, 2026Raymond Chua, Doina Precup, Blake RichardsPlasticity Deep Reinforcement Learning
Word Class Representations Spontaneously Emerge from Successor Representations Trained on Natural Language
May 23, 2026Mathis Immertreu, Achim Schilling, Thomas Kinfe +1Syntactic Structure Semantic Representations
Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning
May 13, 2026Stefan Stojanovic, Alexandre ProutiereHierarchical Reinforcement Learning Goal-Conditioned Reinforcement Learning
Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
May 12, 2026Ethan Parks, Dalal AlharthiMulti-Agent Reasoning Consensus
Sheaf-Theoretic Planning: A Categorical Foundation for Resilient Multi-Agent Autonomous Systems
May 3, 2026Manuel Hernández, Eduardo Sánchez-SotoMulti-Agent Systems Classical Planning
Benchmarking Testing in Automated Theorem Proving
Apr 26, 2026Jongyoon Kim, Hojae Han, Seung-won HwangTheorem Proof
Hierarchical Active Inference using Successor Representations
Apr 17, 2026Prashant Rangarajan, Rajesh P. N. RaoHierarchical Reinforcement Learning Classical Planning
Successor-Generator Planning with LLM-generated Heuristics
Jan 30, 2025Alexander Tuisov, Yonatan Vernik, Alexander ShleyfmanClassical Planning Heuristics

Aug 26, 2026 · cs.LGJ/K move · Enter open · S save

It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning

Liam P. H. Mertens, Lucas N. Alegre, Florent Delgrange, Diederik M. Roijers+2

AI Lab, Vrije Universiteit Brussel, Belgium · Institute of Informatics - Federal University of Rio Grande do Sul · Federation University Australia

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.

Successor Representations Expected Utility Constrained Reinforcement Learning Temporal Scales

Open paper Ask about it PDF