CTAS achieves over 2 脳 speedup of the average running time, compared with the single best solver. More importantly, CTAS is the first feature-free approach that notably outperforms classical AS models, showing huge potential of applying deep learning to AS tasks.Kangfei Zhao...
"Neural Combinatorial Optimization with Reinforcement Learning"[Bello+, 2016], Traveling Salesman Problem solver - Rintarooo/TSP_DRL_PtrNet
Code Issues Pull requests "Neural Combinatorial Optimization with Reinforcement Learning"[Bello+, 2016], Traveling Salesman Problem solver deep-reinforcement-learning pytorch pointer-networks tsp actor-critic active-search Updated Oct 27, 2021 Python map...
Generalization in Deep RL for TSP Problems via Equivariance and Local Search Article29 March 2024 Notes 1. https://github.com/MichelDeudon/encode-attend-navigate. References Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning...
GOPS: A general optimal control problem solver for autonomous driving and industrial control applications 2023, Communications in Transportation Research Citation Excerpt : The most inspiring advance is the work of DeepMind (Degrave et al., 2022), which successfully controls a variety of plasma shapes...