RESEARCH · RESEARCH · #1462
MIT's Cathy Wu and team develop RL problem-selection algorithm that can boost training efficiency up to 30× (2023)
Researchers led by MIT professor Cathy Wu identified RL sensitivity across related traffic problems and in 2023 devised an algorithm that selects the subset of problems on which RL trains well; by training on those problems and combining resulting models the team reported up to 30× improvement in training efficiency and better generalization across related transportation tasks. The work builds on Wu's earlier 2018 RL traffic study and a 2022 diagnosis of RL fragility across similar problems.
KEY POINTS
- Researchers led by MIT professor Cathy Wu identified RL sensitivity across related traffic problems and in 2023 devised an algorithm that selects the subset of problems on which RL trains well; by training on those problems and combining resulting models the team reported up to 30× improvement in training efficiency and better generalization across related transportation tasks.
- The work builds on Wu's earlier 2018 RL traffic study and a 2022 diagnosis of RL fragility across similar problems.
- If robust, this problem-selection approach could make reinforcement learning practical and far more efficient for designing and evaluating complex transportation systems.
WHY IT MATTERS
If robust, this problem-selection approach could make reinforcement learning practical and far more efficient for designing and evaluating complex transportation systems.