satellite scheduling

2 items

RESEARCHarXiv CS.AI·4/16/2026

Optimizing Earth Observation Satellite Schedules under Unknown Operational Constraints: An Active Constraint Acquisition Approach

This paper addresses Earth Observation satellite scheduling under unknown operational constraints, which must be learned interactively from a binary oracle. The authors introduce Conservative Constraint Acquisition (CCA), a domain-specific procedure, to efficiently identify justified constraints for a simplified model.

Optimization machine learning Constraint Acquisition satellite scheduling

RESEARCHarXiv CS.AI·4/7/2026

When Adaptive Rewards Hurt: Causal Probing and the Switching-Stability Dilemma in LLM-Guided LEO Satellite Scheduling

Este artigo de pesquisa explora o design adaptativo de recompensas para DRL no agendamento de satélites LEO, revelando um dilema de estabilidade onde pesos de recompensa estáticos superam os dinâmicos devido à necessidade de um sinal quase estacionário para o PPO. O estudo introduz um método de sondagem causal para identificar a alavancagem de termos de recompensa específicos, descobrindo que um aumento na penalidade de switching melhora significativamente a taxa de dados.

Deep Reinforcement Learning satellite scheduling Reward Design