Characterizing Flow Complexity in Transportation Networks using Graph Homology

no code implementations • 9 Mar 2024 • Shashank A Deshpande, Hamsa Balakrishnan

We propose a graph homology with robust $k$-paths as the bases of its chain spaces.

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

1 code implementation • 3 Nov 2022 • Siddharth Nayak, Kenneth Choi, Wenqi Ding, Sydney Dolan, Karthik Gopalakrishnan, Hamsa Balakrishnan

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent.

Collision Avoidance Multi-agent Reinforcement Learning +2

NICE: Robust Scheduling through Reinforcement Learning-Guided Integer Programming

1 code implementation • 24 Sep 2021 • Luke Kenworthy, Siddharth Nayak, Christopher Chin, Hamsa Balakrishnan

We compare NICE with (1) a baseline integer programming formulation that produces a feasible crew schedule, and (2) a robust integer programming formulation that explicitly tries to minimize the impact of disruptions.

reinforcement-learning Reinforcement Learning (RL) +1