Tabular RL on a Non-Markovian Rewards Decision Process formulation matches deep RL performance on real metro expansion in Xi'an and Amsterdam while cutting episodes by 18x and carbon emissions by 12x on average.
Varshney, and Caiming Xiong
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning
Tabular RL on a Non-Markovian Rewards Decision Process formulation matches deep RL performance on real metro expansion in Xi'an and Amsterdam while cutting episodes by 18x and carbon emissions by 12x on average.