Benjamin Rosman

113 papers A* 19A 9B 2C 2Journal 63Unranked 18

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents. CoRR Simon Rosen, Siddarth Singh, Ebenezer Gelo, Helen Sarah Robertson, Ibrahim Suder, Victoria Williams, Benjamin Rosman, Geraud Nangue Tasse, Steven D. James
2026	J	`jnl`	Unsupervised Hierarchical Skill Discovery. CoRR Damion Harvey, Geraud Nangue Tasse, Branden Ingram, Benjamin Rosman, Steven James
2026	—	`conf`	Who Gets Represented in Robot Intelligence? Human-Robot Interaction, Societal Context, and the Future of Autonomy (Keynote). HRI Companion Benjamin Rosman
2025	J	`jnl`	Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments. CoRR Geraud Nangue Tasse, Matthew Riemer, Benjamin Rosman, Tim Klinger
2025	J	`jnl`	Composition and Zero-Shot Transfer with Lattice Structures in Reinforcement Learning. J. Artif. Intell. Res. Geraud Nangue Tasse, Steven James, Benjamin Rosman
2025	J	`jnl`	Compositional Instruction Following with Language Models and Reinforcement Learning. CoRR Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew C. Gombolay, Raymond J. Mooney, Benjamin Rosman
2025	—	`conf`	Culturally Sensitive Social Robotics for Africa. CR@HRI Adedayo Akinade, Daniel Barros, E. Birhan, M. Danso, Yohannes Haile, I. Jimoh, C. Osano, Pravesh Ranchod, M. Richard, Benjamin Rosman, Birhanu Shimelis Girma, T. Taye Tefferi, David Vernon
2025	J	`jnl`	Heartificial Intelligence: Exploring Empathy in Language Models. CoRR Victoria Williams, Benjamin Rosman
2025	B	`conf`	M-SAT: Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Actions. IJCNN Perusha Moodley, Dhillu Thambi, Mark Trovinger, Pramod Kaushik, Praveen Paruchuri, Xia Hong, Benjamin Rosman
2025	A*	`conf`	Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks. ICLR Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe
2025	J	`jnl`	Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks. CoRR Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe
2025	J	`jnl`	Revisiting the Role of Relearning in Semantic Dementia. CoRR Devon Jarvis, Verena Klar, Richard Klein, Benjamin Rosman, Andrew M. Saxe
2025	J	`jnl`	Source-Free Elastic Model Adaptation for Vision-and-Language Navigation. IEEE Trans. Multim. Mingkui Tan, Peihao Chen, Hongyan Zhi, Jiajie Mai, Benjamin Rosman, Dongyu Ji, Runhao Zeng
2025	J	`jnl`	Strengthening Robotics and Automation in Africa: Highlights of ICRA@40-Africa [Education]. IEEE Robotics Autom. Mag. Ndivhuwo Makondo, Paul Amayo, Jenalea Rajab, Lifhasi Ramulondi, Steven James, Alexandra Barry, Adam Mukuddem, Thabisa Maweni, Tamlin Love, Geraud Nangue Tasse, Zimkhitha Sijovu, Belinda Matebese, Benjamin Rosman
2025	—	`conf`	The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource Languages. ACL (1) Jenalea Rajab, Anuoluwapo Aremu, Everlyn Asiko Chimoto, Dale Dunbar, Graham Morrissey, Fadel Thior, Luandrie Potgieter, Jessica Ojo, Atnafu Lambebo Tonja, Wilhelmina Ndapewa Onyothi Nekoto, Pelonomi Moiloa, Jade Z. Abbott, Vukosi Marivate, Benjamin Rosman
2025	J	`jnl`	The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource Languages. CoRR Jenalea Rajab, Anuoluwapo Aremu, Everlyn Asiko Chimoto, Dale Dunbar, Graham Morrissey, Fadel Thior, Luandrie Potgieter, Jessico Ojo, Atnafu Lambebo Tonja, Maushami Chetty, Onyothi Nekoto, Pelonomi Moiloa, Jade Z. Abbott, Vukosi Marivate, Benjamin Rosman
2025	J	`jnl`	TrueReason: An Exemplar Personalised Learning System Integrating Reasoning with Foundational Models. CoRR Sahan Bulathwela, Daniel van Niekerk, Jarrod Shipton, María Pérez-Ortiz, Benjamin Rosman, John Shawe-Taylor
2024	J	`jnl`	Compositional Instruction Following with Language Models and Reinforcement Learning. Trans. Mach. Learn. Res. Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew C. Gombolay, Raymond Mooney, Benjamin Rosman
2024	J	`jnl`	Hierarchically Composing Level Generators for the Creation of Complex Structures. IEEE Trans. Games Michael Beukman, Manuel Fokam, Marcel Kruger, Guy Axelrod, Muhammad Umair Nasir, Branden Ingram, Benjamin Rosman, Steven James
2024	J	`jnl`	InkubaLM: A small language model for low-resource African languages. CoRR Atnafu Lambebo Tonja, Bonaventure F. P. Dossou, Jessica Ojo, Jenalea Rajab, Fadel Thior, Eric Peter Wairagala, Aremu Anuoluwapo, Pelonomi Moiloa, Jade Z. Abbott, Vukosi Marivate, Benjamin Rosman
2024	J	`jnl`	Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces. CoRR Perusha Moodley, Pramod Kaushik, Dhillu Thambi, Mark Trovinger, Praveen Paruchuri, Xia Hong, Benjamin Rosman
2024	J	`jnl`	On The Specialization of Neural Modules. CoRR Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe
2024	J	`jnl`	RobocupGym: A challenging continuous control benchmark in Robocup. CoRR Michael Beukman, Branden Ingram, Geraud Nangue Tasse, Benjamin Rosman, Pravesh Ranchod
2024	A*	`conf`	Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning. ICLR Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman
2024	A*	`conf`	The Zeno's Paradox of 'Low-Resource' Languages. EMNLP Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Benjamin Rosman, Thamar Solorio, Monojit Choudhury
2024	J	`jnl`	The Zeno's Paradox of 'Low-Resource' Languages. CoRR Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Benjamin Rosman, Thamar Solorio, Monojit Choudhury
2024	J	`jnl`	Towards Financially Inclusive Credit Products Through Financial Time Series Clustering. CoRR Tristan Bester, Benjamin Rosman
2024	J	`jnl`	Transferable dynamics models for efficient object-oriented reinforcement learning. Artif. Intell. Ofir Marom, Benjamin Rosman
2023	J	`jnl`	Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure. CoRR Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse
2023	—	`conf`	Creating Diverse Play-Style-Centric Agents through Behavioural Cloning. AIIDE Branden Ingram, Clint J. van Alten, Richard Klein, Benjamin Rosman
2023	A*	`conf`	Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies. NeurIPS Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman
2023	J	`jnl`	Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies. CoRR Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman
2023	J	`jnl`	FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation. ACM Trans. Hum. Robot Interact. O. Can Görür, Benjamin Rosman, Fikret Sivrikaya, Sahin Albayrak
2023	J	`jnl`	Generalisable Agents for Neural Network Optimisation. CoRR Kale-ab Abebe Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius
2023	J	`jnl`	Generating Interpretable Play-Style Descriptions Through Deep Unsupervised Clustering of Trajectories. IEEE Trans. Games Branden Ingram, Clint J. van Alten, Richard Klein, Benjamin Rosman
2023	—	`conf`	Hierarchical WaveFunction Collapse. AIIDE Michael Beukman, Branden Ingram, Ireton Liu, Benjamin Rosman
2023	J	`jnl`	Hierarchically Composing Level Generators for the Creation of Complex Structures. CoRR Michael Beukman, Manuel Fokam, Marcel Kruger, Guy Axelrod, Muhammad Umair Nasir, Branden Ingram, Benjamin Rosman, Steven James
2023	A*	`conf`	On The Specialization of Neural Modules. ICLR Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M. Saxe
2023	J	`jnl`	Planning to Learn: A Novel Algorithm for Active Learning during Model-Based Planning. CoRR Rowan Hodson, Bruce A. Bassett, Charel van Hoof, Benjamin Rosman, Mark Solms, Jonathan P. Shock, Ryan Smith
2023	J	`jnl`	ROSARL: Reward-Only Safe Reinforcement Learning. CoRR Geraud Nangue Tasse, Tamlin Love, Mark Nemecek, Steven James, Benjamin Rosman
2023	A	`conf`	The Challenge of Redundancy on Multi-agent Value Factorisation. AAMAS Siddarth Shandeep Singh, Benjamin Rosman
2023	J	`jnl`	The challenge of redundancy on multi-agent value factorisation. CoRR Siddarth Singh, Benjamin Rosman
2023	J	`jnl`	Who should I trust? Cautiously learning with unreliable experts. Neural Comput. Appl. Tamlin Love, Ritesh Ajoodha, Benjamin Rosman
2022	J	`jnl`	A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education. CoRR Herkulaas MvE Combrink, Vukosi Marivate, Benjamin Rosman
2022	A*	`conf`	Autonomous Learning of Object-Centric Abstractions for High-Level Planning. ICLR Steven James, Benjamin Rosman, George Konidaris
2022	J	`jnl`	Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases. CoRR Herkulaas MvE Combrink, Vukosi Marivate, Benjamin Rosman
2022	A*	`conf`	Generalisation in Lifelong Reinforcement Learning through Logical Composition. ICLR Geraud Nangue Tasse, Steven James, Benjamin Rosman
2022	C	`conf`	Improved Action Prediction through Multiple Model Processing of Player Trajectories. CoG Branden Ingram, Benjamin Rosman, Clint J. van Alten, Richard Klein
2022	J	`jnl`	Learning Abstract and Transferable Representations for Planning. CoRR Steven James, Benjamin Rosman, George Dimitri Konidaris
2022	C	`conf`	Play-style Identification through Deep Unsupervised Clustering of Trajectories. CoG Branden Ingram, Benjamin Rosman, Clint J. van Alten, Richard Klein
2022	—	`conf`	Real Time In-Game Playstyle Classification Using a Hybrid Probabilistic Supervised Learning Approach. SACAIR Lindsay John Arendse, Branden Ingram, Benjamin Rosman
2022	—	`conf`	Reducing the Planning Horizon Through Reinforcement Learning. ECML/PKDD (4) Logan Dunbar, Benjamin Rosman, Anthony G. Cohn, Matteo Leonetti
2022	J	`jnl`	Reinforcement Learning in Education: A Multi-Armed Bandit Approach. CoRR Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman
2022	—	`conf`	Reinforcement Learning in Education: A Multi-armed Bandit Approach. AFRICATEK Herkulaas MvE Combrink, Vukosi Marivate, Benjamin Rosman
2022	J	`jnl`	Skill Machines: Temporal Logic Composition in Reinforcement Learning. CoRR Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman
2022	J	`jnl`	World Value Functions: Knowledge Representation for Learning and Planning. CoRR Geraud Nangue Tasse, Benjamin Rosman, Steven James
2022	J	`jnl`	World Value Functions: Knowledge Representation for Multitask Reinforcement Learning. CoRR Geraud Nangue Tasse, Steven James, Benjamin Rosman
2021	J	`jnl`	Applying a principle of explicability to AI research in Africa: should we do it? Ethics Inf. Technol. Mary Carman, Benjamin Rosman
2021	J	`jnl`	FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation. CoRR O. Can Görür, Benjamin Rosman, Fikret Sivrikaya, Sahin Albayrak
2021	J	`jnl`	Fairness and accountability of AI in disaster risk management: Opportunities and challenges. Patterns Caroline M. Gevaert, Mary Carman, Benjamin Rosman, Yola Georgiadou, Robert Soden
2021	J	`jnl`	Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization. CoRR Kale-ab Abebe Tessera, Sara Hooker, Benjamin Rosman
2021	J	`jnl`	Learning to Follow Language Instructions with Compositional Policies. CoRR Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew C. Gombolay, Benjamin Rosman
2020	A*	`conf`	A Boolean Task Algebra for Reinforcement Learning. NeurIPS Geraud Nangue Tasse, Steven James, Benjamin Rosman
2020	J	`jnl`	A Boolean Task Algebra for Reinforcement Learning. CoRR Geraud Nangue Tasse, Steven James, Benjamin Rosman
2020	J	`jnl`	A Remote Sensing Method to Monitor Water, Aquatic Vegetation, and Invasive Water Hyacinth at National Extents. Remote. Sens. Geethen Singh, Chevonne Reynolds, Marcus Byrne, Benjamin Rosman
2020	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. Pattern Recognit. Lett. Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2020	A*	`conf`	Learning Portable Representations for High-Level Planning. ICML Steven James, Benjamin Rosman, George Konidaris
2020	J	`jnl`	Online Constrained Model-based Reinforcement Learning. CoRR Benjamin van Niekerk, Andreas C. Damianou, Benjamin Rosman
2020	A*	`conf`	Utilising Uncertainty for Efficient Learning of Likely-Admissible Heuristics. ICAPS Ofir Marom, Benjamin Rosman
2019	A	`conf`	Anticipatory Bayesian Policy Selection for Online Adaptation of Collaborative Robots to Unknown Human Types. AAMAS O. Can Görür, Benjamin Rosman, Sahin Albayrak
2019	A*	`conf`	Composing Value Functions in Reinforcement Learning. ICML Benjamin van Niekerk, Steven James, Adam Christopher Earle, Benjamin Rosman
2019	J	`jnl`	Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks. CoRR Adam Pantanowitz, Emmanuel Cohen, Philippe Gradidge, Nigel Crowther, Vered Aharonson, Benjamin Rosman, David M. Rubin
2019	J	`jnl`	If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks. CoRR Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon
2019	J	`jnl`	Learning Portable Representations for High-Level Planning. CoRR Steven James, Benjamin Rosman, George Dimitri Konidaris
2019	J	`jnl`	Symbol Emergence in Cognitive Developmental Systems: A Survey. IEEE Trans. Cogn. Dev. Syst. Tadahiro Taniguchi, Justus H. Piater, Florentin Wörgötter, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Öztop
2019	J	`jnl`	Transfer Learning for Prosthetics Using Imitation Learning. CoRR Montaser Mohammedalamen, Waleed D. Khamies, Benjamin Rosman
2019	—	`conf`	Understanding Structure of Concurrent Actions. SGAI Conf. Perusha Moodley, Benjamin Rosman, Xia Hong
2018	J	`jnl`	A Non-Linear Manifold Alignment Approach to Robot Learning from Demonstrations. J. Robotics Mechatronics Ndivhuwo Makondo, Michihisa Hiratsuka, Benjamin Rosman, Osamu Hasegawa
2018	A*	`conf`	Accelerating Model Learning with Inter-Robot Knowledge Transfer. ICRA Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa
2018	A*	`conf`	Belief Reward Shaping in Reinforcement Learning. AAAI Ofir Marom, Benjamin Rosman
2018	—	`conf`	Hierarchical Subtask Discovery with Non-Negative Matrix Factorization. ICLR (Poster) Adam Christopher Earle, Andrew M. Saxe, Benjamin Rosman
2018	—	`conf`	Implementation of A Neural Natural Language Understanding Component for Arabic Dialogue Systems. ACLING Abdallah M. Bashir, Abubakr Hassan, Benjamin Rosman, Daniel Duma, Mohanad Ahmed
2018	—	`conf`	Learning the Influence Structure between Partially Observed Stochastic Processes Using IoT Sensor Data. AAAI Workshops Ritesh Ajoodha, Benjamin Rosman
2018	A	`conf`	Real-Time Motion Planning in Changing Environments Using Topology-Based Encoding of Past Knowledge. IROS Richard Fisher, Benjamin Rosman, Vladimir Ivan
2018	J	`jnl`	Reasoning about Unforeseen Possibilities During Policy Learning. CoRR Craig Innes, Alex Lascarides, Stefano V. Albrecht, Subramanian Ramamoorthy, Benjamin Rosman
2018	A*	`conf`	Social Cobots: Anticipatory Decision-Making for Collaborative Robots Incorporating Unexpected Human Behaviors. HRI O. Can Görür, Benjamin Rosman, Fikret Sivrikaya, Sahin Albayrak
2018	J	`jnl`	Symbol Emergence in Cognitive Developmental Systems: a Survey. CoRR Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Öztop, Justus H. Piater, Florentin Wörgötter
2018	J	`jnl`	Will it Blend? Composing Value Functions in Reinforcement Learning. CoRR Benjamin van Niekerk, Steven James, Adam Christopher Earle, Benjamin Rosman
2018	A*	`conf`	Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning. NeurIPS Ofir Marom, Benjamin Rosman
2017	A*	`conf`	An Analysis of Monte Carlo Tree Search. AAAI Steven James, George Dimitri Konidaris, Benjamin Rosman
2017	B	`conf`	Fingerprint minutiae extraction using deep learning. IJCB Luke Nicholas Darlow, Benjamin Rosman
2017	J	`jnl`	Hierarchical Subtask Discovery With Non-Negative Matrix Factorization. CoRR Adam Christopher Earle, Andrew M. Saxe, Benjamin Rosman
2017	A*	`conf`	Hierarchy Through Composition with Multitask LMDPs. ICML Andrew M. Saxe, Adam Christopher Earle, Benjamin Rosman
2017	A	`conf`	Online Constrained Model-based Reinforcement Learning. UAI Benjamin van Niekerk, Andreas C. Damianou, Benjamin Rosman
2016	A	`conf`	A Bayesian Approach for Learning and Tracking Switching, Non-Stationary Opponents: (Extended Abstract). AAMAS Pablo Hernandez-Leal, Benjamin Rosman, Matthew E. Taylor, Luis Enrique Sucar, Enrique Munoz de Cote
2016	J	`jnl`	Bayesian policy reuse. Mach. Learn. Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy
2016	J	`jnl`	Hierarchy through Composition with Linearly Solvable Markov Decision Processes. CoRR Andrew M. Saxe, Adam Christopher Earle, Benjamin Rosman
2016	—	`conf`	Identifying and Tracking Switching, Non-Stationary Opponents: A Bayesian Approach. AAAI Workshop: Multiagent Interaction without Prior Coordination Pablo Hernandez-Leal, Matthew E. Taylor, Benjamin Rosman, Luis Enrique Sucar, Enrique Munoz de Cote
2016	A	`conf`	Trajectory learning from human demonstrations via manifold mapping. IROS Michihisa Hiratsuka, Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa
2015	J	`jnl`	Action Priors for Learning Domain Invariances. IEEE Trans. Auton. Ment. Dev. Benjamin Rosman, Subramanian Ramamoorthy
2015	J	`jnl`	Bayesian Policy Reuse. CoRR Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy
2015	—	`conf`	Enhancing agent safety through autonomous environment adaptation. ICDL-EPIROB Benjamin Rosman, Bradley Hayes, Brian Scassellati
2015	—	`conf`	Knowledge transfer for learning robot models via Local Procrustes Analysis. Humanoids Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa
2015	A	`conf`	Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning. IROS Pravesh Ranchod, Benjamin Rosman, George Dimitri Konidaris
2014	—	`conf`	Feature selection for domain knowledge representation through multitask learning. ICDL-EPIROB Benjamin Rosman
2014	A*	`conf`	Giving advice to agents with hidden goals. ICRA Benjamin Rosman, Subramanian Ramamoorthy
2014	—	`conf`	Modelling Primate Control of Grasping for Robotics Applications. ECCV Workshops (2) Ashley Kleinhans, Serge Thill, Benjamin Rosman, Renaud Detry, Bryan P. Tripp
2014	A	`conf`	On user behaviour adaptation under interface change. IUI Benjamin Rosman, Subramanian Ramamoorthy, M. M. Hassan Mahmud, Pushmeet Kohli
2013	J	`jnl`	Clustering Markov Decision Processes For Continual Transfer. CoRR M. M. Hassan Mahmud, Majd Hawasly, Benjamin Rosman, Subramanian Ramamoorthy
2012	—	`conf`	What good are actions? Accelerating learning using learned action priors. ICDL-EPIROB Benjamin Rosman, Subramanian Ramamoorthy
2011	J	`jnl`	Learning spatial relationships between objects. Int. J. Robotics Res. Benjamin Rosman, Subramanian Ramamoorthy
2010	A*	`conf`	A game-theoretic procedure for learning hierarchically structured strategies. ICRA Benjamin Rosman, Subramanian Ramamoorthy
2006	A	`conf`	Language performance at high school and success in first year computer science. SIGCSE Sarah Rauchas, Benjamin Rosman, George Dimitri Konidaris, Ian D. Sanders