Knowledge areas
Reinforcement Learning, Human-aligned AI, AI safety
Publications
Balanced Q-learning: Combining the influence of optimistic and pessimistic targets
T George Karimpanal, H Le, M Abdolshah, S Rana, S Gupta, T Tran, S Venkatesh
(2023), Vol. 325, Artificial Intelligence, C1
Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer
B Semage, T Karimpanal, S Rana, S Venkatesh
(2023), Vol. 13644, pp. 674-686, ICPR 2022 : Pattern Recognition, Computer Vision, and Image Processing. ICPR 2022 International Workshops and Challenges Montreal, QC, Canada, August 21–25, 2022, Proceedings, Part II, Montreal, Quebec, E1
Controlled Diversity with Preference: Towards Learning a Diverse Set of Desired Skills
M Hussonnois, T Karimpanal, S Rana
(2023), Vol. 2023-May, pp. 1135-1143, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, E1
Sympathy-based Reinforcement Learning Agents
M Senadeera, T Karimpanal, S Gupta, S Rana
(2022), Vol. 2, pp. 1164-1172, Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, E1
Fast Model-based Policy Search for Universal Policy Networks
B Semage, T George Karimpanal, S Rana, S Venkatesh
(2022), Vol. 2022-August, pp. 2314-2320, ICPR 2022 : Proceedings of the 26th International Conference on Pattern Recognition, Montreal, Quebec, E1
Uncertainty Aware System Identification with Universal Policies
B Semage, T George Karimpanal, S Rana, S Venkatesh
(2022), Vol. 2022-August, pp. 2321-2327, ICPR 2022 : Proceedings of the 26th International Conference on Pattern Recognition, Montreal, Quebec, E1
Episodic Policy Gradient Training
H Le, M Abdolshah, T George, K Do, D Nguyen, S Venkatesh
(2022), Vol. 36, pp. 7317-7325, Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, E1
Learning to Constrain Policy Optimization with Virtual Trust Region
H Le, T George, M Abdolshah, D Nguyen, K Do, S Gupta, S Venkatesh
(2022), Vol. 35, Advances in Neural Information Processing Systems, E1
A New Representation of Successor Features for Transfer across Dissimilar Environments
Majid Abdolshah, Hung Le, Thommen George, Sunil Gupta, Santu Rana, Svetha Venkatesh
(2021), Vol. 139, pp. 1-14, ICML 2021 : Proceedings of the International Conference of Machine Learning, Virtual Conference, E1
Model-Based Episodic Memory Induces Dynamic Hybrid Controls
H Le, H Le, T George, T George, M Abdolshah, M Abdolshah, T Tran, T Tran, S Venkatesh, S Venkatesh
(2021), Vol. 36, pp. 1-26, NeurIPS 2021 : Proceedings of the 35th Conference on Neural Information Processing Systems, Virtual Conference, E1
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
T Karimpanal, S Rana, S Gupta, T Tran, S Venkatesh
(2020), pp. 1-10, IJCNN 2020 : Proceedings of the 2020 International Joint Conference on Neural Networks, Glasgow, Scotland, E1
Self-organizing maps for storage and transfer of knowledge in reinforcement learning
T George Karimpanal, R Bouffanais
(2019), Vol. 27, pp. 111-126, Adaptive Behavior, C1
Experience Replay Using Transition Sequences
Thommen Karimpanal, Roland Bouffanais
(2018), Vol. 12, FRONTIERS IN NEUROROBOTICS, Switzerland, C1
A self-replication basis for designing complex agents
T Karimpanal George
(2018), pp. 45-46, GECCO '18 : Proceedings of the Genetic and Evolutionary Computation Conference, Kyoto, Japan, E1
Identification and off-policy learning of multiple objectives using adaptive clustering
Thommen Karimpanal, Erik Wilhelm
(2017), Vol. 263, pp. 39-47, NEUROCOMPUTING, C1
Sensing discomfort of standing passengers in public rail transportation systems using a smart phone
Thommen George, Harit Gadhia, Ruben, John-John Cabibihan
(2013), pp. 1509-1513, 2013 10TH IEEE INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA), Hangzhou, PEOPLES R CHINA, E1-1
Funded Projects at Deakin
No Funded Projects at Deakin found
Supervisions
Buddhika Semage
Thesis entitled: Robust and Efficient Reinforcement Learning for Physics Tasks
Doctor of Philosophy (Information Technology), Applied Artificial Intel Ins