2 papers
cs.LG2026
Federated Distributional Reinforcement Learning with Distributional Critic Regularization
David Millard, Cecilia Alm, Rashid Ali +2
Federated reinforcement learning typically aggregates value functions or policies by parameter averaging, which emphasizes expected return and can obscure statistical multimodality…
cs.AI2025
Hierarchical Neuro-Symbolic Decision Transformer
Ali Baheri, Cecilia O. Alm
We present a hierarchical neuro-symbolic control framework that tightly couples a classical symbolic planner with a transformer-based policy to address long-horizon decision-making…