Zaheer Abbas
Zaheer Abbas
Research Engineer, Google DeepMind
Bestätigte E-Mail-Adresse bei
Zitiert von
Zitiert von
Gemini: a family of highly capable multimodal models
G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ...
arXiv preprint arXiv:2312.11805, 2023
Organizing experience: a deeper look at replay mechanisms for sample-based planning in continuous state domains
Y Pan, Z Abbas, A White, A Patterson, M White
IJCAI'18, 2018
General value function networks
M Schlegel, A Jacobsen, Z Abbas, A Patterson, A White, M White
arXiv preprint arXiv:1807.06763, 2018
Selective Dyna-style Planning Under Limited Model Capacity
Z Abbas, S Sokota, EJ Talvitie, M White
ICML'20, 2020
Loss of Plasticity in Continual Deep Reinforcement Learning
Z Abbas, R Zhao, J Modayil, A White, MC Machado
arXiv preprint arXiv:2303.07507, 2023
Planning with expectation models
Y Wan, Z Abbas, A White, M White, RS Sutton
IJCAI'19, 2019
Investigating the Properties of Neural Network Representations in Reinforcement Learning
H Wang, E Miahi, M White, MC Machado, Z Abbas, R Kumaraswamy, ...
arXiv preprint arXiv:2203.15955, 2022
From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning
B Rafiee, Z Abbas, S Ghiassian, R Kumaraswamy, R Sutton, E Ludvig, ...
arXiv preprint arXiv:2011.04590, 2020
Model-based reinforcement learning with non-linear expectation models and stochastic environments
Y Wan, Z Abbas, M White, RS Sutton
FAIM Workshop on Prediction and Generative Modeling in Reinforcement …, 2018
Selective Dyna-style Planning Using Neural Network Models with Limited Capacity
Z Abbas
Incrementally Learning Functions of the Return
B Bennett, W Chung, Z Abbas, V Liu
arXiv preprint arXiv:1907.04651, 2019
Towards model-free RL algorithms that scale well with unstructured data
J Modayil, Z Abbas
arXiv preprint arXiv:2311.02215, 2023
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–12