DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
Dec 10, 2023
Speakers
Jiarui Wang
Speaker · 0 followers
Zhiguang Cao
Speaker · 0 followers
Helan Liang
Speaker · 0 followers
About
Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally, customizing ACO for a specific problem requires the expert design of knowledge-driven heuristics. In this paper, we propose DeepACO, a generic framework leveraging deep reinforcement learning to automate heuristic designs. DeepACO serves to strengthen the heuristic measures of existing ACO algorithms and dispense with laborious manual design in future ACO applications. As a neural-enhanced meta-heuristic, DeepACO consistently outperforms its ACO counterparts on eight COPs using a single neural model and a single set of hyperparameters. As a Neural Combinatorial Optimization (NCO) method, DeepACO also performs better than or competitively against the problem-specific methods on the canonical Travelling Salesman Problem.Ant Colony Optimization (ACO) is a meta-heuristic algorithm that has been successfully applied to various Combinatorial Optimization Problems (COPs). Traditionally, customizing ACO for a specific problem requires the expert design of knowledge-driven heuristics. In this paper, we propose DeepACO, a generic framework leveraging deep reinforcement learning to automate heuristic designs. DeepACO serves to strengthen the heuristic measures of existing ACO algorithms and dispense with laborious manua…
Organizer
NeurIPS 2023
Account · 622 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
Watch later
Zhiyu Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Group Robust Classification Without Any Group Information
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
HEIM: Holistic Evaluation of Text-to-Image Models
Watch later
Tony Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Watch later
Jiazheng Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Watch later
Jan Dubiński, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Offline Reinforcement Learning for Mixture of Expert Dialogue Management
Watch later
Dhawal Gupta, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%