Подписаться
Akhil Bagaria
Akhil Bagaria
PhD Student, Brown University
Подтвержден адрес электронной почты в домене brown.edu - Главная страница
Название
Процитировано
Процитировано
Год
Option Discovery using Deep Skill Chaining
GK Akhil Bagaria
International Conference on Learning Representations (ICLR), 2020
138*2020
Skill discovery for exploration and planning using deep skill graphs
A Bagaria, JK Senthil, G Konidaris
International Conference on Machine Learning, 521-531, 2021
582021
Robustly Learning Composable Options in Deep Reinforcement Learning
A Bagaria, J Senthil, M Slivinski, G Konidaris
International Joint Conferences on Artificial Intelligence Organization …, 2021
252021
Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning
S Lobel, A Bagaria, G Konidaris
The Fortieth International Conference on Machine Learning (ICML), 0
19*
Optimistic initialization for exploration in continuous control
S Lobel, O Gottesman, C Allen, A Bagaria, G Konidaris
Proceedings of the AAAI Conference on Artificial Intelligence 36 (7), 7612-7619, 2022
142022
Effectively learning initiation sets in hierarchical reinforcement learning
A Bagaria, B Abbatematteo, O Gottesman, M Corsaro, S Rammohan, ...
Advances in Neural Information Processing Systems 36, 73441-73463, 2023
32023
Scaling Goal-based Exploration via Pruning Proto-goals
A Bagaria, R Jiang, R Kumar, T Schaul
International Joint Conferences on Artificial Intelligence (IJCAI) 2023, 2023
32023
Sphynx: A Shared Instruction Cache Exporatory Study
D Park, A Bagaria, F Hannan, E Storm, J Spjut
arXiv preprint arXiv:1412.1140, 2014
2014
Structured Exploration in Reinforcement Learning by Hypothesizing Linear Temporal Logic Formulas
Y Wei, X Li, JX Liu, N Shah, B Quartey, G Konidaris, S Tellex, A Bagaria
2nd CoRL Workshop on Learning Effective Abstractions for Planning, 0
Learning Portable Skills by Identifying Generalizing Features with an Attention-Based Ensemble
ATDM Koch, Z Zhou, A Bagaria, H Fu, C Allen, G Konidaris
Termination Classifiers for Image-Based Observation Spaces
JWN Lim, A Bagaria, G Konidaris, S Sridhar
[Replication] A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
A Bagaria, S Kim, A Mazzetto, R Rodriguez-Sanchez
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–12