← Search

Romina Abachi

2 accepted papers

2025

Calibrated Value-Aware Model Learning with Probabilistic Environment Models

ICML 2025poster

The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several pro…

Cited by 0SourcePDFScholar
2022

Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation

AAAI 2022technical

The shortcomings of maximum likelihood estimation in the context of model-based reinforcement learning have been highlighted by an increasing number of papers. When the model class is misspecified or has a limited representational capacity, model parameters with high likelihood might not necessarily…