5 papers
Refined outer-approximation algorithms for monotonic optimisation
Ahmed Rashwan
Monotonic optimisation is a broad class of non-convex problems formulated in terms of monotone functions. Such problems are commonly solved via the polyblock outer-approximation al…
Monotone Optimisation with Learned Projections
Ahmed Rashwan, Keith Briggs, Chris Budd +1
Monotone optimisation problems admit specialised global solvers such as the Polyblock Outer Approximation (POA) algorithm, but these methods typically require explicit objective an…
Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
Ahmed Rashwan, Keith Briggs, Chris Budd +1
Credit assignment is a core challenge in multi-agent reinforcement learning (MARL), especially in large-scale systems with structured, local interactions. Graph-based Markov decisi…
Enforcing convex constraints in Graph Neural Networks
Ahmed Rashwan, Keith Briggs, Chris Budd +1
Many machine learning applications require outputs that satisfy complex, dynamic constraints. This task is particularly challenging in Graph Neural Network models due to the variab…
A neural drift-plus-penalty algorithm for network power allocation and routing
Ahmed Rashwan, Keith Briggs, Chris Budd
The drift-plus-penalty method is a Lyapunov optimisation technique commonly applied to network routing problems. It reduces the original stochastic planning task to a sequence of g…