E-LIB Suche - Ergebnisse für: George Karimpanal, Thommen

1

Balanced Q-learning: Combining the influence of optimistic ..:

George Karimpanal, Thommen ; Le, Hung ; Abdolshah, Majid...
Artificial Intelligence. 325 (2023) - p. 104021 , 2023

Link: https://doi.org/10.1016/..

2

Fast Model-based Policy Search for Universal Policy Network:

, In: 2022 26th International Conference on Pattern Recognition (ICPR),

Semage, Buddhika Laknath ; George Karimpanal, Thommen ; Rana, Santu. - p. 2314-2320 , 2022

Link: https://doi.org/10.1109/..

3

Uncertainty Aware System Identification with Universal Poli..:

, In: 2022 26th International Conference on Pattern Recognition (ICPR),

Semage, Buddhika Laknath ; George Karimpanal, Thommen ; Rana, Santu. - p. 2321-2327 , 2022

Link: https://doi.org/10.1109/..

4

Self-organizing maps for storage and transfer of knowledge ..:

George Karimpanal, Thommen ; Bouffanais, Roland
Adaptive Behavior. 27 (2018) 2 - p. 111-126 , 2018

Link: https://doi.org/10.1177/..

5

Intuitive Physics Guided Exploration for Sample Efficient S..:

, In: Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges; Lecture Notes in Computer Science,

Semage, Buddhika Laknath ; Karimpanal, Thommen George ; Rana, Santu. - p. 674-686 , 2023

Link: https://doi.org/10.1007/..

6

Human-aligned reinforcement learning for autonomous agents ..:

Cruz, Francisco ; Karimpanal, Thommen George ; Solis, Miguel A...
Neural Computing and Applications. 35 (2023) 23 - p. 16689-16691 , 2023

Link: https://doi.org/10.1007/..

7

Learning Transferable Domain Priors for Safe Exploration in..:

, In: 2020 International Joint Conference on Neural Networks (IJCNN),

Karimpanal, Thommen George ; Rana, Santu ; Gupta, Sunil.. - p. 1-10 , 2020

Link: https://doi.org/10.1109/..

8

Experience Replay Using Transition Sequences:

Karimpanal, Thommen George ; Bouffanais, Roland
Frontiers in Neurorobotics. 12 (2018) - p. , 2018

Link: https://doi.org/10.3389/..

9

A self-replication basis for designing complex agents:

, In: Proceedings of the Genetic and Evolutionary Computation Conference Companion,

Karimpanal, Thommen George - p. 45-46 , 2018

Link: https://dl.acm.org/doi/1..

10

Identification and off-policy learning of multiple objectiv..:

Karimpanal, Thommen George ; Wilhelm, Erik
Neurocomputing. 263 (2017) - p. 39-47 , 2017

Link: https://doi.org/10.1016/..

11

EMOTE: An Explainable architecture for Modelling the Other ..:

Senadeera, Manisha ; George, Thommen Karimpanal ; Gupta, Sunil..
http://arxiv.org/abs/2306.00295. , 2023

Link: http://arxiv.org/abs/230..

12

Learning to Constrain Policy Optimization with Virtual Trus..:

Le, Hung ; George, Thommen Karimpanal ; Abdolshah, Majid...
http://arxiv.org/abs/2204.09315. , 2022

Link: http://arxiv.org/abs/220..

13

A New Representation of Successor Features for Transfer acr..:

Abdolshah, Majid ; Le, Hung ; George, Thommen Karimpanal...
http://arxiv.org/abs/2107.08426. , 2021

Link: http://arxiv.org/abs/210..

14

Plug and Play, Model-Based Reinforcement Learning:

Abdolshah, Majid ; Le, Hung ; George, Thommen Karimpanal...
http://arxiv.org/abs/2108.08960. , 2021

Link: http://arxiv.org/abs/210..

15

Model-Based Episodic Memory Induces Dynamic Hybrid Controls:

Le, Hung ; George, Thommen Karimpanal ; Abdolshah, Majid..
http://arxiv.org/abs/2111.02104. , 2021

Link: http://arxiv.org/abs/211..