Learning Combinatorial Optimzation

Learning Combinatorial Optimization Algorithms Over Graphs

Learning Combinatorial Optimization Over Graphs

Roles Abhi (intro), Pranav/Avlin (actual paper), Daniel (Conclusion: performance, adv, disadv, criticism)

Intro 1) Graph Theory (MLP, TSP, Maxcut) - Common Problems to Solve are: Minimum Vertex Cover: Given a ‘graph’ G, find the minimum number of vertices to tick, so that every single edge is covered. G=(V,E,w). Where G is the Graph, V are the vertices, E is the edge, and w is the optimal solution Maximum Cut: Given a ‘graph’ G, Travelling Salesman Problem

2) Reinforcement Learning -

Actual Paper:

Conclusions (Performance, advantages, disadvantages): A3C? S2V?

Criticism: