activity
20242026
collaborators
Showing cs.LGShow all

14 papers · 1 filter

cs.LG2026

Learning to Perceive the World Through Control: Empowerment-Based Representation Learning

Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach

In many practical reinforcement learning environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn repres…

cs.LG2026

Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization

Alireza Modirshanechi, Benjamin Eysenbach, Peter Dayan +1

Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, a…

cs.LG2026

Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning

Bill Chunyuan Zheng, Vivek Myers, Benjamin Eysenbach +1

Learning how to reach goals in an environment is a longstanding challenge in AI, yet reasoning over long horizons remains a challenge for modern methods. The key question is how to…

cs.LG2026

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Kevin Wang, Ishaan Javali, Michał Bortkiewicz +2

Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we…

cs.LG2025

Accelerating Goal-Conditioned RL Algorithms and Research

Michał Bortkiewicz, Władysław Pałucki, Vivek Myers +4

Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While self-supervised…

cs.LG2025

Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL

Mahsa Bastankhah, Grace Liu, Dilip Arumugam +2

In this work, we take a first step toward elucidating the mechanisms behind emergent exploration in unsupervised reinforcement learning. We study Single-Goal Contrastive Reinforcem…