Follow
Thommen George Karimpanal
Thommen George Karimpanal
Applied Artificial Intelligence Institute
Verified email at deakin.edu.au - Homepage
Title
Cited by
Cited by
Year
Self-organizing maps for storage and transfer of knowledge in reinforcement learning
TG Karimpanal, R Bouffanais
Adaptive Behavior, 1059712318818568, 2019
39*2019
Sensing discomfort of standing passengers in public rail transportation systems using a smart phone
TG Karimpanal, HM Gadhia, R Sukumar, JJ Cabibihan
IEEE International Conference on Control and Automation (ICCA) 2013 …, 2013
20*2013
Identification and off-policy learning of multiple objectives using adaptive clustering
TG Karimpanal, E Wilhelm
Neurocomputing 263, 39-47, 2017
162017
Experience Replay Using Transition Sequences
TG Karimpanal, R Bouffanais
Frontiers in Neurorobotics 12, 32, 2018
92018
Self-Organizing Maps as a Storage and Transfer Mechanism in Reinforcement Learning
TG Karimpanal, R Bouffanais
Autonomous Agents and Multiagent Systems (AAMAS), 2018, Stockholm, Adaptive …, 2018
82018
Adapting Low-Cost Platforms for Robotics Research
TG Karimpanal, M Chamanbaz, W Li, T Jeruzalski, A Gupta, E Wilhelm
International Conference on Intelligent Robots and Systems (IROS), 2015 …, 2015
52015
A New Representation of Successor Features for Transfer across Dissimilar Environments
M Abdolshah, H Le, TG Karimpanal, S Gupta, S Rana, S Venkatesh
International Conference on Machine Learning, 1-9, 2021
42021
Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
TG Karimpanal, S Rana, S Gupta, T Tran, S Venkatesh
International Joint Conference on Neural Networks (IJCNN), 2020, Glasgow …, 2020
42020
Model-Based Episodic Memory Induces Dynamic Hybrid Controls
H Le, TG Karimpanal, M Abdolshah, T Tran, S Venkatesh
NeurIPS 2021, 2021
32021
A Self-Replication Basis for Designing Complex Agents
TG Karimpanal
Genetic and Evolutionary Computation Conference (GECCO), 2018, In …, 2018
22018
Modeling and Simulation of the Dynamics of the Quick Return Mechanism: A Bond Graph Approach
TG Karimpanal, A Vaz
Industrial Problems on Machines and Mechanisms (IPRoMM), 2010, Jaipur, India …, 2010
2*2010
Sympathy-based Reinforcement Learning Agents
M Senadeera, TG Karimpanal, S Gupta, S Rana
Proceedings of the 21st International Conference on Autonomous Agents and …, 2022
12022
Episodic Policy Gradient Training
H Le, M Abdolshah, TG Karimpanal, K Do, D Nguyen, S Venkatesh
AAAI 2022, 2021
12021
Neuro-evolutionary Frameworks for Generalized Learning Agents
TG Karimpanal
arXiv preprint arXiv:2002.01088, 2020
12020
Memory-Constrained Policy Optimization
H Le, TG Karimpanal, M Abdolshah, D Nguyen, K Do, S Gupta, ...
arXiv preprint arXiv:2204.09315, 2022
2022
Uncertainty Aware System Identification with Universal Policies
BL Semage, TG Karimpanal, S Rana, S Venkatesh
International Conference on Pattern Recognition (ICPR), 2022, 2022
2022
Fast Model-based Policy Search for Universal Policy Networks
BL Semage, TG Karimpanal, S Rana, S Venkatesh
International Conference on Pattern Recognition (ICPR), 2022, 2022
2022
Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets
TG Karimpanal, H Le, M Abdolshah, S Rana, S Gupta, T Tran, ...
arXiv preprint arXiv:2111.02787, 2021
2021
Reachability Traces for Curriculum Design in Reinforcement Learning
TG Karimpanal, M Abdolshah, H Le, S Rana, S Gupta, T Tran, ...
2021
Neural Latent Traversal with Semantic Constraints
M Abdolshah, H Le, TG Karimpanal, V Le, S Gupta, S Rana, S Venkatesh
2021
The system can't perform the operation now. Try again later.
Articles 1–20