Follow
James Kostas
James Kostas
PhD Student, University of Massachusetts Amherst
Verified email at umass.edu - Homepage
Title
Cited by
Cited by
Year
Learning action representations for reinforcement learning
Y Chandak, G Theocharous, J Kostas, S Jordan, P Thomas
International Conference on Machine Learning, 941-950, 2019
1812019
Asynchronous Coagent Networks
J Kostas, C Nota, P Thomas
International Conference on Machine Learning, 5426-5435, 2020
12*2020
Structural Credit Assignment in Neural Networks using Reinforcement Learning
D Gupta, G Mihucz, M Schlegel, J Kostas, PS Thomas, M White
Advances in Neural Information Processing Systems 34, 2021
62021
Seldonian toolkit: Building software with safe and fair machine learning
A Hoag, JE Kostas, BC da Silva, PS Thomas, Y Brun
2023 IEEE/ACM 45th International Conference on Software Engineering …, 2023
32023
High Confidence Generalization for Reinforcement Learning
J Kostas, Y Chandak, SM Jordan, G Theocharous, P Thomas
International Conference on Machine Learning, 5764-5773, 2021
32021
Coagent Networks: Generalized and Scaled
JE Kostas, SM Jordan, Y Chandak, G Theocharous, D Gupta, M White, ...
arXiv preprint arXiv:2305.09838, 2023
12023
Generating recommendations utilizing an edge-computing-based asynchronous coagent network
J Kostas, G Theocharous
US Patent App. 17/514,768, 2023
2023
Edge-Compatible Reinforcement Learning for Recommendations
JE Kostas, PS Thomas, G Theocharous
arXiv preprint arXiv:2112.05812, 2021
2021
Classical Policy Gradient: Preserving Bellman's Principle of Optimality
PS Thomas, SM Jordan, Y Chandak, C Nota, J Kostas
arXiv preprint arXiv:1906.03063, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–9