A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper uses DeePC to improve urban traffic lights, reducing congestion and emissions.
SUMO provides unbiased log marginal likelihood estimation for latent variable models.
Methodology to analyze traffic accidents using microscopic models.
Survival regression method improves log-likelihood scores.
Bayesian model for energy-efficient EV navigation.
The common pipeline in autonomous driving systems is highly modular and includes a perception component which extracts lists of surrounding objects and passes these lists to a high-level decision component. In this case, leveraging the benefits of deep reinforcement learning for high-level decision making requires spec…
A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient explo…
Study tackles balancing policy switching costs in offline RL.
Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, o…
Existing inefficient traffic light control causes numerous problems, such as long delay and waste of energy. To improve efficiency, taking real-time traffic information as an input and dynamically adjusting the traffic light duration accordingly is a must. In terms of how to dynamically adjust traffic signals' duration…
New algorithm improves self-play reinforcement learning for competitive games.
Proposes Constrained Q-learning for reinforcement learning with constraints.
New algorithms speed up inverse reinforcement learning by solving MDPs once.