Thommen George Karimpanal

51 papers A* 4A 4B 3Journal 34Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs. EACL (Findings) Omar Mahmoud, Ali Khalil, Thommen George Karimpanal, Buddhika Laknath Semage, Santu Rana
2025	A*	`conf`	Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer. IJCAI Minh Hoang Nguyen, Linh Le Pham Van, Thommen George Karimpanal, Sunil Gupta, Hung Le
2025	J	`jnl`	Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer. CoRR Minh Hoang Nguyen, Linh Le Pham Van, Thommen George Karimpanal, Sunil Gupta, Hung Le
2025	A	`conf`	Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment. AAMAS Maxence Hussonnois, Thommen George Karimpanal, Santu Rana
2025	J	`jnl`	Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment. CoRR Maxence Hussonnois, Thommen George Karimpanal, Santu Rana
2025	J	`jnl`	Human-informed skill discovery: Controlled diversity with preference in reinforcement learning. Expert Syst. Appl. Maxence Hussonnois, Thommen George Karimpanal, Mayank Shekhar Jha, Santu Rana
2025	J	`jnl`	Improving Multilingual Language Models by Aligning Representations through Steering. CoRR Omar Mahmoud, Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana
2025	A	`conf`	MAGIK: Mapping to Analogous Goals via Imagination-Enabled Knowledge Transfer. ECAI Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana
2025	J	`jnl`	MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer. CoRR Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana
2025	J	`jnl`	The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs. CoRR Omar Mahmoud, Ali Khalil, Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana
2024	—	`conf`	ECoDe: A Sample-Efficient Method for Co-design of Robotic Agents. AI (2) Kishan R. Nagiredla, Buddhika Laknath Semage, Arun Kumar Anjanapura Venkatesh, Thommen George Karimpanal, Santu Rana
2024	J	`jnl`	Personalisation via Dynamic Policy Fusion. CoRR Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana
2023	J	`jnl`	Balanced Q-learning: Combining the influence of optimistic and pessimistic targets. Artif. Intell. Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh
2023	A	`conf`	Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills. AAMAS Maxence Hussonnois, Thommen George Karimpanal, Santu Rana
2023	J	`jnl`	Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills. CoRR Maxence Hussonnois, Thommen George Karimpanal, Santu Rana
2023	J	`jnl`	Human-aligned reinforcement learning for autonomous agents and robots. Neural Comput. Appl. Francisco Cruz, Thommen George Karimpanal, Miguel A. Solis, Pablo Barros, Richard Dazeley
2023	J	`jnl`	LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying. CoRR Thommen George Karimpanal, Buddhika Laknath Semage, Santu Rana, Hung Le, Truyen Tran, Sunil Gupta, Svetha Venkatesh
2023	J	`jnl`	Sample-Efficient Co-Design of Robotic Agents Using Multi-fidelity Training on Universal Policy Network. CoRR Kishan R. Nagiredla, Buddhika Laknath Semage, Thommen George Karimpanal, Arun Kumar A. V., Santu Rana
2023	J	`jnl`	Zero-shot Sim2Real Adaptation Across Environments. CoRR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2022	A*	`conf`	Episodic Policy Gradient Training. AAAI Hung Le, Majid Abdolshah, Thommen George Karimpanal, Kien Do, Dung Nguyen, Svetha Venkatesh
2022	B	`conf`	Fast Model-based Policy Search for Universal Policy Networks. ICPR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2022	J	`jnl`	Fast Model-based Policy Search for Universal Policy Networks. CoRR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2022	—	`conf`	Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer. ICPR Workshops (2) Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2022	J	`jnl`	Memory-Constrained Policy Optimization. CoRR Hung Le, Thommen George Karimpanal, Majid Abdolshah, Dung Nguyen, Kien Do, Sunil Gupta, Svetha Venkatesh
2022	A	`conf`	Sympathy-based Reinforcement Learning Agents. AAMAS Manisha Senadeera, Thommen George Karimpanal, Sunil Gupta, Santu Rana
2022	B	`conf`	Uncertainty Aware System Identification with Universal Policies. ICPR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2022	J	`jnl`	Uncertainty Aware System Identification with Universal Policies. CoRR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2021	A*	`conf`	A New Representation of Successor Features for Transfer across Dissimilar Environments. ICML Majid Abdolshah, Hung Le, Thommen George Karimpanal, Sunil Gupta, Santu Rana, Svetha Venkatesh
2021	J	`jnl`	A New Representation of Successor Features for Transfer across Dissimilar Environments. CoRR Majid Abdolshah, Hung Le, Thommen George Karimpanal, Sunil Gupta, Santu Rana, Svetha Venkatesh
2021	J	`jnl`	Balanced Q-learning: Combining the Influence of Optimistic and Pessimistic Targets. CoRR Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh
2021	J	`jnl`	Episodic Policy Gradient Training. CoRR Hung Le, Majid Abdolshah, Thommen George Karimpanal, Kien Do, Dung Nguyen, Svetha Venkatesh
2021	J	`jnl`	Intuitive Physics Guided Exploration for Sample Efficient Sim2real Transfer. CoRR Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh
2021	A*	`conf`	Model-Based Episodic Memory Induces Dynamic Hybrid Controls. NeurIPS Hung Le, Thommen George Karimpanal, Majid Abdolshah, Truyen Tran, Svetha Venkatesh
2021	J	`jnl`	Model-Based Episodic Memory Induces Dynamic Hybrid Controls. CoRR Hung Le, Thommen George Karimpanal, Majid Abdolshah, Truyen Tran, Svetha Venkatesh
2021	J	`jnl`	Plug and Play, Model-Based Reinforcement Learning. CoRR Majid Abdolshah, Hung Le, Thommen George Karimpanal, Sunil Gupta, Santu Rana, Svetha Venkatesh
2020	B	`conf`	Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning. IJCNN Thommen George Karimpanal, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh
2020	J	`jnl`	Neuro-evolutionary Frameworks for Generalized Learning Agents. CoRR Thommen George Karimpanal
2019	J	`jnl`	Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning. CoRR Thommen George Karimpanal, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh
2019	J	`jnl`	Self-organizing maps for storage and transfer of knowledge in reinforcement learning. Adapt. Behav. Thommen George Karimpanal, Roland Bouffanais
2018	J	`jnl`	A Self-Replication Basis for Designing Complex Agents. CoRR Thommen George Karimpanal
2018	—	`conf`	A self-replication basis for designing complex agents. GECCO (Companion) Thommen George Karimpanal
2018	J	`jnl`	Experience Replay Using Transition Sequences. Frontiers Neurorobotics Thommen George Karimpanal, Roland Bouffanais
2018	J	`jnl`	Self-Organizing Maps as a Storage and Transfer Mechanism in Reinforcement Learning. CoRR Thommen George Karimpanal, Roland Bouffanais
2018	J	`jnl`	Self-Organizing Maps for Storage and Transfer of Knowledge in Reinforcement Learning. CoRR Thommen George Karimpanal, Roland Bouffanais
2017	J	`jnl`	Adapting Low-Cost Platforms for Robotics Research. CoRR Thommen George Karimpanal, Mohammadreza Chamanbaz, Wenzheng Li, Timothy Jeruzalski, Abhishek Gupta, Erik Wilhelm
2017	J	`jnl`	Experience Replay Using Transition Sequences. CoRR Thommen George Karimpanal, Roland Bouffanais
2017	J	`jnl`	Identification and Off-Policy Learning of Multiple Objectives Using Adaptive Clustering. CoRR Thommen George Karimpanal, Erik Wilhelm
2017	J	`jnl`	Identification and off-policy learning of multiple objectives using adaptive clustering. Neurocomputing Thommen George Karimpanal, Erik Wilhelm
2017	J	`jnl`	Sensing discomfort of standing passengers in public rail transportation systems using a smart phone. CoRR Thommen George Karimpanal, Harit Maganlal Gadhia, Ruben Sukumar, John-John Cabibihan
2015	—	`conf`	Adapting Low-Cost Platforms for Robotics Research. FinE-R@IROS Thommen George Karimpanal, Mohammadreza Chamanbaz, Wenzheng Li, Timothy Jeruzalski, Abhishek Gupta, Erik Wilhelm
2013	—	`conf`	Sensing discomfort of standing passengers in public rail transportation systems using a smart phone. ICCA Thommen George Karimpanal, Harit Maganlal Gadhia, Ruben Sukumar, John-John Cabibihan