Search Results for author:
Found 12 papers, 11 papers with code
PARCO: Learning Parallel Autoregressive Policies for Efficient Multi-Agent Combinatorial Optimization
Multi-agent combinatorial optimization problems such as routing and scheduling have great practical relevance but present challenges due to their NP-hard combinatorial nature, hard constraints on the number of possible agents, and hard-to-optimize objective functions.
RouteFinder: Towards Foundation Models for Vehicle Routing Problems
Our core idea is that a foundation model for VRPs should be able to represent variants by treating each as a subset of a generalized problem equipped with different attributes.
Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding
To further improve the performance of the communication-based MARL-MAPF solvers, we propose a new method, Ensembling Prioritized Hybrid Policies (EPH).
Multi-Agent Path Finding
Multi-agent Reinforcement Learning
+1
HiMAP: Learning Heuristics-Informed Policies for Large-Scale Multi-Agent Pathfinding
With a simple training scheme and implementation, HiMAP demonstrates competitive results in terms of success rate and scalability in the field of imitation-learning-only MAPF, showing the potential of imitation-learning-only MAPF equipped with inference techniques.
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
The omnipresence of NP-hard combinatorial optimization problems (COPs) compels domain experts to engage in trial-and-error heuristic design.
Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
While complex simulations of physical systems have been widely used in engineering and scientific computing, lowering their often prohibitive computational requirements has only recently been tackled by deep learning approaches.
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems.
Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
The subsequent stage involves bootstrapping, which augments the training dataset with self-generated data labeled by a proxy score function.
Transform Once: Efficient Operator Learning in Frequency Domain
Instead, this work introduces a blueprint for frequency domain learning through a single transform: transform once (T1).
Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction
In this paper, we propose Meta-SysId, a meta-learning approach to model sets of systems that have behavior governed by common but unknown laws and that differentiate themselves by their context.
DevFormer: A Symmetric Transformer for Context-Aware Device Placement
In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization.
Neural Solvers for Fast and Accurate Numerical Optimal Control
Synthesizing optimal controllers for dynamical systems often involves solving optimization problems with hard real-time constraints.
