Physics priors written as symbolic programs constrain a PPO agent's action choices, yielding better zero-shot wireless indoor navigation and 26%+ training-time savings on Gibson maps.
Deep learning based wireless localization for indoor navigation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation
Physics priors written as symbolic programs constrain a PPO agent's action choices, yielding better zero-shot wireless indoor navigation and 26%+ training-time savings on Gibson maps.