← Search

Sergio Hernández-Gutiérrez

2 accepted papers

2026

Intrinsic Credit Assignment for Long Horizon Interaction

ICML 2026poster

How can we train agents to navigate uncertainty over long horizons? In this work, we propose ∆Belief-RL, which leverages a language model's own intrinsic beliefs to reward intermediate progress. Our method utilizes the change in the probability an agent assigns to the target solution for credit assi…

Cited by 0SourceScholar
2025

Co-Adaptation of Embodiment and Control with Self-Imitation Learning

IROS 2025

The task of co-optimizing the body and behaviour of agents has been a long-standing problem in the fields of evolutionary robotics and embodied AI. Previous work has largely focused on the development of learning methods exploiting massive parallelization of agent evaluations with large population s

Cited by 0SourceScholar