2025
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Claas A Voelcker, Anastasiia Pedan, Arash Ahmadian, Romina Abachi, Igor Gilitschenski, Amir-massoud Farahmand
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…