Mahsa Bastankhah — accepted AI-conference papers

2026

Demystifying Emergent Exploration in Goal-Conditioned RL

Mahsa Bastankhah, Grace Liu, Dilip Arumugam, Thomas L. Griffiths, Benjamin Eysenbach

ICLR 2026poster

In this work, we take a first step toward elucidating the mechanisms behind emergent exploration in unsupervised reinforcement learning. We study Single-Goal Contrastive Reinforcement Learning (SGCRL) (Liu et al., 2025), a self-supervised algorithm capable of solving challenging long-horizon goal-re…

Cited by 0 Source ↗Scholar ↗

2026

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

Mahsa Bastankhah, Sophie Broderick, Benjamin Eysenbach

ICML 2026poster

In many practical reinforcement learning (RL) environments, observations are far higher-dimensional than the variables that matter for control. In this work, we ask: can we learn representations that capture only control-relevant features of the environment? We study this question through the \emph{…

Cited by 0 Source ↗Scholar ↗