Follow
Shauharda Khadka
Shauharda Khadka
Senior Data & Applied Scientist at Microsoft
Verified email at microsoft.com
Title
Cited by
Cited by
Year
Evolution-guided policy gradient in reinforcement learning
S Khadka, K Tumer
Advances in Neural Information Processing Systems 31, 2018
277*2018
Collaborative evolutionary reinforcement learning
S Khadka, S Majumdar, T Nassar, Z Dwiel, E Tumer, S Miret, Y Liu, ...
Proceedings of the International Conference on Machine Learning, 3341-3350, 2019
1332019
Evolutionary reinforcement learning for sample-efficient multiagent coordination
S Majumdar, S Khadka, S Miret, S McAleer, K Tumer
International Conference on Machine Learning, 6651-6660, 2020
612020
Artificial intelligence for prosthetics: Challenge solutions
Ł Kidziński, C Ong, SP Mohanty, J Hicks, S Carroll, B Zhou, H Zeng, ...
The NeurIPS'18 Competition: From Machine Learning to Intelligent …, 2020
422020
Evolving memory-augmented neural architecture for deep memory problems
S Khadka, JJ Chung, K Tumer
Proceedings of the Genetic and Evolutionary Computation Conference, 441-448, 2017
172017
Neuroevolution of a modular memory-augmented neural network for deep memory problems
S Khadka, JJ Chung, K Tumer
Evolutionary computation 27 (4), 639-664, 2019
152019
Optimizing memory placement using evolutionary graph reinforcement learning
S Khadka, E Aflalo, M Marder, A Ben-David, S Miret, S Mannor, T Hazan, ...
arXiv preprint arXiv:2007.07298, 2020
132020
Learning intrinsic symbolic rewards in reinforcement learning
HU Sheikh, S Khadka, S Miret, S Majumdar, M Phielipp
2022 International Joint Conference on Neural Networks (IJCNN), 1-8, 2022
122022
Multi-level fitness critics for cooperative coevolution
G Rockefeller, S Khadka, K Tumer
AAMAS Conference proceedings, 2020
112020
Maedys: Multiagent evolution via dynamic skill selection
E Sachdeva, S Khadka, S Majumdar, K Tumer
Proceedings of the Genetic and Evolutionary Computation Conference, 163-171, 2021
62021
A memory-based multiagent framework for adaptive decision making
S Khadka, C Yates, K Tumer
Proceedings of the 17th International Conference on Autonomous Agents and …, 2018
62018
Neuroevolution of a hybrid power plant simulator
S Khadka, K Tumer, M Colby, D Tucker, P Pezzini, K Bryden
Proceedings of the Genetic and Evolutionary Computation Conference 2016, 917-924, 2016
62016
Memory-augmented multi-robot teams that learn to adapt
S Khadka, JJ Chung, K Tumer
2017 International Symposium on Multi-Robot and Multi-Agent Systems (MRS …, 2017
42017
Dynamic skill selection for learning joint actions
E Sachdeva, S Khadka
Autonomous agents and multiagent systems, 2021
12021
Automatic multi-objective hardware optimization for processing of deep learning networks
M Marder, E Aflalo, A Ben-David, S Khadka, S Majumdar, S Miret, H Tang
US Patent App. 17/129,521, 2021
2021
Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences
S Majumdar, S Khadka, S Miret, S Mcaleer, K Tumer
2020
Memory-Based Multiagent One-Shot Learning
S Khadka, C Yates, K Tumer
2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS …, 2019
2019
Tackling Credit Assignment Using Memory and Multilevel Optimization for Multiagent Reinforcement Learning
S Khadka
2019
Fabrication of Oxygenation Microfluidic Devices for Cell Cultures
DTE Shauharda Khadka, Gerardo Mauleon
Journal of Undergraduate Research 7 (1), 5-9, 2014
2014
The system can't perform the operation now. Try again later.
Articles 1–19