Следене
Ishan Durugkar
Ishan Durugkar
Research Scientist, Sony AI
Потвърден имейл адрес: sony.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning
R Das, S Dhuliawala, M Zaheer, L Vilnis, I Durugkar, A Krishnamurthy, ...
arXiv preprint arXiv:1711.05851, 2017
6782017
Generative Multi-Adversarial Networks
I Durugkar, I Gemp, S Mahadevan
International Conference on Learning Representations, 2017, 2017
4792017
Cohort intelligence: a self supervised learning behavior
AJ Kulkarni, IP Durugkar, M Kumar
2013 IEEE international conference on systems, man, and cybernetics, 1396-1400, 2013
1412013
Predictive off-policy policy evaluation for nonstationary decision problems, with applications to digital marketing
P Thomas, G Theocharous, M Ghavamzadeh, I Durugkar, E Brunskill
Proceedings of the AAAI Conference on Artificial Intelligence 31 (2), 4740-4745, 2017
672017
An imitation from observation approach to transfer learning with dynamics mismatch
S Desai, I Durugkar, H Karnan, G Warnell, J Hanna, P Stone
Advances in Neural Information Processing Systems 33, 3917-3929, 2020
622020
Adversarial intrinsic motivation for reinforcement learning
I Durugkar, M Tec, S Niekum, P Stone
Advances in Neural Information Processing Systems 34, 8622-8636, 2021
442021
Deep reinforcement learning with macro-actions
IP Durugkar, C Rosenbaum, S Dernbach, S Mahadevan
arXiv preprint arXiv:1606.04615, 2016
312016
Balancing individual preferences and shared objectives in multiagent reinforcement learning
I Durugkar, E Liebman, P Stone
International Joint Conference on Artificial Intelligence, 2020
252020
Reducing sampling error in batch temporal difference learning
B Pavse, I Durugkar, J Hanna, P Stone
International Conference on Machine Learning, 7543-7552, 2020
162020
TD learning with constrained gradients
I Durugkar, P Stone
152018
f-policy gradients: A general framework for goal-conditioned rl using f-divergences
S Agarwal, I Durugkar, P Stone, A Zhang
Advances in Neural Information Processing Systems 36, 12100-12123, 2023
72023
Towards a real-time, low-resource, end-to-end object detection pipeline for robot soccer
SK Narayanaswami, M Tec, I Durugkar, S Desai, B Masetty, S Narvekar, ...
Robot World Cup, 62-74, 2022
72022
Wasserstein distance maximizing intrinsic control
I Durugkar, S Hansen, S Spencer, V Mnih
arXiv preprint arXiv:2110.15331, 2021
42021
Unmixing in the presence of nuisances with deep generative models
M Parente, I Gemp, I Durugkar
2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS …, 2017
32017
N-agent ad hoc teamwork
C Wang, MA Rahman, I Durugkar, E Liebman, P Stone
Advances in Neural Information Processing Systems 37, 111832-111862, 2025
22025
Estimation and control of visitation distributions for reinforcement learning
I Durugkar
22023
Abc: Adversarial behavioral cloning for offline mode-seeking imitation learning
E Hudson, I Durugkar, G Warnell, P Stone
arXiv preprint arXiv:2211.04005, 2022
22022
DM : Distributed multi-agent reinforcement learning via distribution matching
C Wang
22022
An imitation from observation approach to sim-to-real transfer
S Desai, I Durugkar, H Karnan, G Warnell, J Hanna, P Stone, AI Sony
2nd Workshop on Closing the Reality Gap in Sim2Real Transfer for Robotics. RSS, 2020
22020
Multi-preference actor critic
I Durugkar, M Hausknecht, A Swaminathan, P MacAlpine
arXiv preprint arXiv:1904.03295, 2019
22019
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20