2 papers
cs.LG2024
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte +1
Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime. That said, popular goal representations, e.g., target states or natural lang…
cs.AI2024
Entropy-regularized Point-based Value Iteration
Harrison Delecki, Marcell Vazquez-Chanlatte, Esen Yel +4
Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based…