Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Categorical semantics of compositional reinforcement learning
Georgios Bakirtzis, Michail Savvas, Ufuk Topcu
Compositional knowledge representations in reinforcement learning (RL) facilitate modular, interpretable, and safe task specifications. However, generating compositional models req…
cs.AI2025
Reduce, Reuse, Recycle: Categories for Compositional Reinforcement Learning
Georgios Bakirtzis, Michail Savvas, Ruihan Zhao +2
In reinforcement learning, conducting task composition by forming cohesive, executable sequences from multiple tasks remains challenging. However, the ability to (de)compose tasks…