Urmăriți
Khimya Khetarpal
Khimya Khetarpal
Research Scientist, Deepmind
Adresă de e-mail confirmată pe mail.mcgill.ca - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Towards continual reinforcement learning: A review and perspectives
K Khetarpal, M Riemer, I Rish, D Precup
[JAIR 2022] Journal of Artificial Intelligence Research 75, 1401-1476, 2022
1162022
What can I do here? A Theory of Affordances in Reinforcement Learning
K Khetarpal, Z Ahmed, G Comanici, D Abel, D Precup
[ICML 2020] International Conference on Machine Learning, 2020
512020
Value preserving state-action abstractions
D Abel, N Umbanhowar, K Khetarpal, D Arumugam, D Precup, M Littman
[AISTATS 2020] International Conference on Artificial Intelligence and …, 2020
372020
Learning Robust State Abstractions for Hidden-Parameter Block MDPs
A Zhang, S Sodhani, K Khetarpal, J Pineau
[ICLR 2021] arXiv preprint arXiv:2007.07206, 2020
30*2020
Options of Interest: Temporal Abstraction with Interest Functions
K Khetarpal, M Klissarov, M Chevalier-Boisvert, PL Bacon, D Precup
[AAAI 2020] Conference on Artificial Intelligence, arXiv preprint arXiv:2001 …, 2020
282020
Safe option-critic: Learning safety in the option-critic architecture
A Jain, K Khetarpal, D Precup
[KER Journal 2021] The Knowledge Engineering Review 36, 2021, 2018
232018
Re-evaluate: Reproducibility in evaluating reinforcement learning algorithms
K Khetarpal, Z Ahmed, A Cianflone, R Islam, J Pineau
[ICML Workshop 2018], Reproducibility in ML Workshop,, 2018
20*2018
Sequoia: A software framework to unify continual learning research
F Normandin, F Golemo, O Ostapenko, P Rodriguez, MD Riemer, ...
[ICML Workshop 2021] Workshop on Theory and Foundation of Continual Learning, 2021
16*2021
Self-Supervised Attention-Aware Reinforcement Learning
H Wu, K Khetarpal, D Precup
[AAAI 2021], Conference on Artificial Intelligence, 2021
132021
Variational state encoding as intrinsic motivation in reinforcement learning
M Klissarov, R Islam, K Khetarpal, D Precup
[ICLR Workshop 2019], Task-Agnostic Reinforcement Learning Workshop, 2019
92019
Environments for lifelong reinforcement learning
K Khetarpal, S Sodhani, S Chandar, D Precup
[NeurIPS Workshop 2018], Continual Learning Workshop, arXiv preprint arXiv …, 2018
92018
Variance Penalized On-Policy and Off-Policy Actor-Critic
A Jain, G Patil, A Jain, K Khetarpal, D Precup
[AAAI 2021], Conference on Artificial Intelligence, arXiv preprint arXiv …, 2021
72021
Learning Options with Interest Functions
K Khetarpal, D Precup
[AAAI Student Abstract 2019], 3 Minute Thesis Finalist, 33, 9955-9956, 2019
72019
Mobile robot navigation using evolving neural controller in unstructured environments
A Patnaik, K Khetarpal, L Behera
[ACODS 2014] IFAC Proceedings Volumes 47 (1), 758-765, 2014
72014
Attend before you act: Leveraging human visual attention for continual learning
K Khetarpal, D Precup
[ICML Workshop 2018], Lifelong Learning: A Reinforcement Learning Approach …, 2018
62018
A preliminary benchmark of four saliency algorithms on comic art
K Khetarpal, E Jain
[IEEE Workshop 2016], International Conference on Multimedia & Expo Workshop …, 2016
62016
Temporally Abstract Partial Models
K Khetarpal, Z Ahmed, G Comanici, D Precup
[NeurIPS 2021] Advances in Neural Information Processing Systems, 2021
52021
Creating segments and effects on comics by clustering gaze data
I Thirunarayanan, K Khetarpal, S Koppal, OL Meur, J Shea, E Jain
[ACM Journal, 2017] Transactions on Multimedia Computing, Communications …, 2017
42017
The Paradox of Choice: On the Role of Attention in Hierarchical Reinforcement Learning
AC Nica, K Khetarpal, D Precup
[NeurIPS'22 Workshop] All Things Attention: Bridging Different Perspectives …, 2022
1*2022
Discovering Object-Centric Generalized Value Functions From Pixels
S Nath, GR Subbaraj, K Khetarpal, SE Kahou
[ICML 2023] arXiv preprint arXiv:2304.13892, 2023
2023
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20