Publications

Muhammad Umair Nasir, Steven James, Julian Togelius. GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps. Advances in Neural Information Processing Systems, 2024.

Hellina Hailu Nigatu, Atnafu Lambebo Tonja, Benjamin Rosman, Thamar Solorio, Monojit Choudhury. The Zeno’s Paradox of ‘Low-Resource’ Languages. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024.

Geraud Nangue Tasse, Tamlin Love, Mark Nemecek, Steven James, Benjamin Rosman. ROSARL: Reward-Only Safe Reinforcement Learning. Reinforcement Learning Safety Workshop at RLC, 2024.

Simon Rosen, Abdel Mfougouon Njupoun, Geraud Nangue Tasse, Steven James, Benjamin Rosman. Optimal Task Generalisation in Cooperative Multi-Agent Reinforcement Learning. Coordination and Cooperation in Multi-Agent Reinforcement Learning Workshop at RLC, 2024.

Kayleize Govender, Branden Ingram, Pravesh Ranchod. Analysing the Effect of Latent Space Mutation Strategies for PCGML. In Proceedings of the IEEE Conference on Games, 2024.

Muhammad Umair Nasir, Sam Earle, Christopher Cleghorn, Steven James, Julian Togelius. LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization. In Proceedings of the Genetic and Evolutionary Computation Conference, 2024.

William Hill, Ireton Liu, Anita De Mello Koch, Damion Harvey, Nishanth Kumar, George Konidaris, Steven James. MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds. 6th ICAPS Workshop on the International Planning Competition, 2024.

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman. Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning. In Proceedings of the Twelfth International Conference on Learning Representations, 2024.

Ofir Marom, Benjamin Rosman. Transferable Dynamics Models for Efficient Object-Oriented Reinforcement Learning. Artificial Intelligence, 2024.

Tristan Bester, Benjamin Rosman. Towards Financially Inclusive Credit Products Through Financial Time Series Clustering. AAAI Workshop on AI in Finance for Social Impact, 2024.

Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse. Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure. Workshop on Neuro-Symbolic Learning and Reasoning in the Era of Large Language Models at AAAI, 2024.

David Torpey, Max Parkin, Jonah Alter, Richard Klein, Steven James. MiDaS: A Large-Scale Minecraft Dataset for Non-Natural Image Benchmarking. Journal of Electronic Imaging, 2024.

Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman. Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies. In Advances in Neural Information Processing Systems, 2023.

Junkyu Lee, Michael Katz, Don Joven Agravante, Miao Liu, Geraud Nangue Tasse, Tim Klinger, Shirin Sohrabi. Hierarchical Reinforcement Learning with AI Planning Models. NeurIPS Workshop on Generalization in Planning, 2023.

Kale-ab Tessera, Callum Tilbury, Sasha Abramowitz, Ruan de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius. Generalisable Agents for Neural Network Optimisation. Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization at NeurIPS, 2023.

Eric Rosen, Steven James, Sergio Orozco, Vedant Gupta, Max Merlin, Stefanie Tellex, George Konidaris. Synthesizing Navigation Abstractions for Planning with Portable Manipulation Skills. In Conference on Robot Learning, 2023.

Michael Beukman, Branden Ingram, Ireton Liu, Benjamin Rosman. Hierarchical WaveFunction Collapse. In AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2023.

Branden Ingram, Clint van Alten, Richard Klein, Benjamin Rosman. Creating Diverse Play-Style-Centric Agents through Behavioural Cloning. In AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2023.

Beatrice van Eden, Nicolene Botha, Benjamin Rosman. A Comparison of Visual Place Recognition Methods using a Mobile Robot in an Indoor Environment. RAPDASA-RobMech-PRASA-CoSAAMI Conference, 2023.

Nathan Michlo, Richard Klein, Steven James. Overlooked Implications of the Reconstruction Loss for VAE Disentanglement. Proceedings of the Thirty-second International Joint Conference on Artificial Intelligence, 2023.

Devon Jarvis, Verena Klar, Richard Klein, Benjamin Rosman, Andrew Saxe. Revisiting the Role of Relearning in Semantic Dementia. Conference on Cognitive Computational Neuroscience, 2023.

Branden Ingram. Play-style Identification and Player Modelling for Generating Tailored Advice in Video Games. [Doctoral Thesis] University of the Witwatersrand, 2023.

Branden Ingram, Clint van Alten, Richard Klein, Benjamin Rosman. Generating Interpretable Play-style Descriptions through Deep Unsupervised Clustering of Trajectories. IEEE Transactions on Games, 2023.

Michael Beukman, Manuel Fokam, Marcel Kruger, Guy Axelrod, Muhammad Umair Nasir, Branden Ingram, Benjamin Rosman, Steven James. Hierarchically Composing Level Generators for the Creation of Complex Structures. IEEE Transactions on Games, 2023.

Muhammad Umair Nasir, Michael Beukman, Steven James, Christopher Cleghorn. Augmentative Topology Agents For Open-ended Learning. Genetic and Evolutionary Computation Conference Companion, 2023.

Siddarth Singh, Benjamin Rosman. The Challenge of Redundancy on Multi-agent Value Factorisation. International Conference on Autonomous Agents and Multiagent Systems, 2023.

Orhan Can Görür, Benjamin Rosman, Fikret Sivrikaya, Sahin Albayrak. FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation. ACM Transactions on Human-Robot Interaction, 2023.

Adam Pacheck, Steven James, George Konidaris, Hadas Kress-Gazit. Automatic Encoding and Repair of Reactive High-Level Tasks with Learned Abstract Representations. The International Journal of Robotics Research, 2023.

Richard Lastrucci, Isheanesu Dzingirai, Jenalea Rajab, Andani Madodonga, Matimba Shingange, Daniel Njini, Vukosi Marivate. Preparing the Vuk'uzenzele and ZA-gov-multilingual South African Multilingual Corpora. Workshop on Resources for African Indigenous Language at EACL, 2023.

Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew Saxe. On The Specialization of Neural Modules. In Proceedings of the Eleventh International Conference on Learning Representations, 2023.

Christopher Currin, Mercy Asiedu, Chris Fourie, Benjamin Rosman, Houcemeddine Turki, Atnafu Tonja, Jade Abbott, Marvellous Ajala, Sadiq Adedayo, Chris Emezue, Daphne Machangara. A Framework for Grassroots Research Collaboration in Machine Learning and Global Health. ICLR Workshop on Machine Learning and Global Health, 2023.

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Raymond Mooney, Benjamin Rosman. End-to-End Learning to Follow Language Instructions with Compositional Policies. Workshop on Language and Robot Learning @ CORL, 2022.

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman. Skill Machines: Temporal Logic Composition in Reinforcement Learning. In Deep Reinforcement Learning Workshop @ NeurIPS 2022, 2022.

Wilhelmina Onyothi Nekoto, Julia Kreutzer, Jenalea Rajab, Millicent Ochieng, Jade Abbott. Participatory Translations of Oshiwambo: Towards Culture Preservation with Language Technology. In Workshop on NLP for Positive Impact @ EMNLP, 2022.

Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman. Reinforcement Learning in Education: A Multi-Armed Bandit Approach. 5th EAI International Conference on Emerging Technologies for Developing Countries, 2022.

Lindsay John Arendse, Branden Ingram, Benjamin Rosman. Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach. In Proceedings of the Third Southern African Conference for AI Research. Part of the book series: Communications in Computer and Information Science, Springer, 2022.

Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman. Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases. In Proceedings of the Third Southern African Conference for AI Research, 2022.

Gerrie Crafford, Benjamin Rosman. Improving Reinforcement Learning with Ensembles of Different Learners. RAPDASA/ROBMECH/PRASA/CoSAAMI International Conference, 2022.

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman. Skill Machines: Temporal Logic Composition in Reinforcement Learning. In Lifelong Learning of High-level Cognitive and Reasoning Skills Workshop @ IROS 2022, 2022.

Tamlin Love, Devon Jarvis, Geraud Nangue Tasse, Branden Ingram, Steven James, Benjamin Rosman. Facilitating Safe Sim-to-Real through Simulator Abstraction and Zero-shot Task Composition. In Lifelong Learning of High-level Cognitive and Reasoning Skills Workshop @ IROS 2022, 2022.

Muhammad Umair Nasir, Steven James, Christopher Cleghorn. Augmentative Topology Agents For Open-ended Learning. In Lifelong Learning of High-level Cognitive and Reasoning Skills Workshop @ IROS 2022, 2022.

Logan Dunbar, Benjamin Rosman, Anthony G. Cohn, Matteo Leonetti. Reducing the Planning Horizon through Reinforcement Learning. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2022.

Tamlin Love, Ritesh Ajoodha, Benjamin Rosman. Who Should I Trust? Cautiously Learning with Unreliable Experts. Neural Computing and Applications, 2022.

Branden Ingram, Benjamin Rosman, Clint van Alten, Richard Klein. Play-style Identification through Deep Unsupervised Clustering of Trajectories. In Proceedings of the IEEE Conference on Games, 2022.

Branden Ingram, Benjamin Rosman, Clint van Alten, Richard Klein. Improved Action Prediction through Multiple Model Processing of Player Trajectories. In Proceedings of the IEEE Conference on Games, 2022.

Kale-ab Tessera, Chiratidzo Matowe, Arnu Pretorius, Benjamin Rosman, Sara Hooker. Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules. Workshop on Dynamic Neural Networks at ICML, 2022.

Nicholas Muir, Steven James. Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content. In Proceedings of 43rd Conference of the South African Institute of Computer Scientists and Information Technologists, 2022.

Michael Vogt, Benjamin Rosman. Analyzing Reinforcement Learning Algorithms for Nitrogen Fertilizer Management in Simulated Crop Growth. In Proceedings of 43rd Conference of the South African Institute of Computer Scientists and Information Technologists, 2022.

Michael Beukman, Christopher Cleghorn, Steven James. Procedural Content Generation using Neuroevolution and Novelty Search for Diverse Video Game Levels. In Proceedings of the Genetic and Evolutionary Computation Conference, 2022.

Geraud Nangue Tasse, Benjamin Rosman, Steven James. World Value Functions: Knowledge Representation for Learning and Planning. Bridging the Gap Between AI Planning and Reinforcement Learning Workshop at ICAPS, 2022.

Geraud Nangue Tasse, Benjamin Rosman, Steven James. World Value Functions: Knowledge Representation for Multitask Reinforcement Learning. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Steven James, Benjamin Rosman, George Konidaris. Learning Abstract and Transferable Representations for Planning. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Tamlin Love, Ritesh Ajoodha, Benjamin Rosman. Harnessing the Wisdom of an Unreliable Crowd for Autonomous Decision Making. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Jarrod Shipton, Benjamin Rosman. Diverse Partner Creation with Partner Prediction for Robust K-Level Reasoning. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Michael Beukman, Michael Mitcheley, Dean Wookey, Steven James, George Konidaris. Adaptive Online Value Function Approximation with Wavelets. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Nathan Michlo, Devon Jarvis, Richard Klein, Steven James. Accounting for the Sequential Nature of States to Learn Representations in Reinforcement Learning. The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision Making, 2022.

Jenalea Rajab. Effect of Tokenisation Strategies for Low-Resourced Southern African Languages. 3rd Workshop on African Natural Language Processing, 2022.

Michael Beukman. Analysing the Effects of Transfer Learning on Low-Resourced Named Entity Recognition Performance. 3rd Workshop on African Natural Language Processing, 2022.

Geraud Nangue Tasse, Steven James, Benjamin Rosman. Generalisation in Lifelong Reinforcement Learning through Logical Composition. In Proceedings of the Tenth International Conference on Learning Representations, 2022.

Steven James, Benjamin Rosman, George Konidaris. Autonomous Learning of Object-Centric Abstractions for High-Level Planning. In Proceedings of the Tenth International Conference on Learning Representations, 2022.

Nishai Kooverjee, Steven James, Terence Van Zyl. Investigating Transfer Learning in Graph Neural Networks. Electronics, 2022.

Ritesh Ajoodha, Benjamin Rosman. Using Score-based Structure Learning to Computationally Learn Direct Influence between Hierarchical Dynamic Bayesian Networks. IEEE Asia-Pacific Conference on Computer Science and Data Engineering, 2021.

Siddarth Singh, Benjamin Rosman. The Challenge of Redundancy on Multi-Agent Value Factorisation. NeurIPS Workshop on Cooperative AI, 2021.

David Poulton, Richard Klein. Improving Pose Estimation through Contextual Activity Fusion. Southern African Conference for Artificial Intelligence Research, 2021.

Geraud Nangue Tasse, Steven James, Benjamin Rosman. Generalisation in Lifelong Reinforcement Learning through Logical Composition. NeurIPS Deep Reinforcement Learning Workshop, 2021.

Raesetje Sefala, Timnit Gebru, Luzango Mfupe, Nyalleng Moorosi, Richard Klein. Constructing a Visual Dataset to Study the Effects of Spatial Apartheid in South Africa. NeurIPS 2021 Datasets and Benchmarks Track, 2021.

Jared Harris-Dewey, Richard Klein. Generative Adversarial Networks for Global Illumination and Indirect Lighting as a Replacement for Ray-tracing in Older GPU Hardware. International Conference in Soft Computing and Machine Intelligence, 2021.

Caroline M. Gevaert, Mary Carman, Benjamin Rosman, Yola Georgiadou, Robert Soden. Fairness and accountability of AI in disaster risk management: Opportunities and challenges. Patterns (Elsevier), 2021.

Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Benjamin Rosman. Learning to Follow Language Instructions with Compositional Policies. AAAI Fall Symposium on AI for Human-Robot Interaction, 2021.

Adam Pantanowitz, Emmanuel Cohen, Philippe Gradidge, Nigel J. Crowther, Vered Aharonson, Benjamin Rosman, David M. Rubin. Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks. Informatics in Medicine Unlocked, 2021.

Tamlin Love, Ritesh Ajoodha, Benjamin Rosman. Should I Trust You? Incorporating Unreliable Expert Advice in Human-Agent Interaction. Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots at ICDL, 2021.

Adam Pantanowitz, Benjamin Rosman, Nigel J. Crowther, David M. Rubin. The Hospital as a Sorting Machine. Informatics in Medicine Unlocked, 2021.

Kale-ab Tessera, Sara Hooker, Benjamin Rosman. Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization. Sparsity in Neural Networks: Advancing Understanding and Practice, 2021.

Lawrence Pratt, Devashen Govender, Richard Klein. Defect Detection and Quantification in Electroluminescence Images of Solar PV Modules using U-net Semantic Segmentation. Renewable Energy, 2021.

Muhammad Omer, Rami Ahmed, Benjamin Rosman, Sharief F. Babikir. Model Predictive-Actor Critic Reinforcement Learning for Dexterous Manipulation. International Conference on Computer, Control, Electrical, and Electronics Engineering, 2021.

Muhammed Saeed, Mohammed Nagdi, Benjamin Rosman, Hiba H.S.M. Ali. Deep Reinforcement Learning for Robotic Hand Manipulation. International Conference on Computer, Control, Electrical, and Electronics Engineering, 2021.

Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman. A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education. Southern African Conference for Artificial Intelligence Research, 2021.

Tlou Boloka, Ndivhuwo Makondo, Benjamin Rosman. Knowledge Transfer using Model-Based Deep Reinforcement Learning. In Proceedings of the IEEE SAUPEC/ROBMECH/PRASA International Conference, 2021.

Geraud Nangue Tasse, Steven James, Benjamin Rosman. A Boolean Task Algebra for Reinforcement Learning. In Advances in Neural Information Processing Systems, 2020.

Geethen Singh, Chevonne Reynolds, Marcus Byrne, Benjamin Rosman. A Remote Sensing Method to Monitor Water, Aquatic Vegetation, and Invasive Water Hyacinth at National Extents. Remote Sensing, 2020.

Ofir Marom, Benjamin Rosman. Utilising Uncertainty for Efficient Learning of Likely-Admissible Heuristics. In International Conference on Automated Planning and Scheduling, 2020.

Ritesh Ajoodha, Benjamin Rosman. Learning the Influence Between Partially Observable Processes Using Score-based Structure Learning. Advances in Science, Technology and Engineering Systems Journal, 2020.

Ritesh Ajoodha, Benjamin Rosman. Discovery of Influence between Processes Represented by Hidden Markov Models. International IOT, Electronics and Mechatronics Conference, 2020.

Geraud Nangue Tasse, Steven James, Benjamin Rosman. Logical Composition for Lifelong Reinforcement Learning. 4th Lifelong Learning Workshop at ICML, 2020.

Steven James, Benjamin Rosman, George Konidaris. Learning Portable Representations for High-Level Planning. International Conference on Machine Learning, 2020.

Steven James, Benjamin Rosman, George Konidaris. Learning Object-Centric Representations for High-Level Planning in Minecraft. Object-Oriented Learning: Perception, Representation, and Reasoning. Workshop at ICML, 2020.

Arnu Pretorius, Elan Van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steven James, Benjamin Rosman, Herman Kamper, Steve Kroon. If Dropout Limits Trainable Depth, Does Critical Initialisation Still Matter? A Large-scale Statistical Analysis on ReLU Networks. Pattern Recognition Letters, 2020.

Mary Carman, Benjamin Rosman. Applying a Principle of Explicability to AI Research in Africa: Should we do it?. Ethics and Information Technology, 2020.

Geraud Nangue Tasse, Steven James, Benjamin Rosman. A Boolean Task Algebra for Reinforcement Learning. Beyond Tabula Rasa in Reinforcement Learning (Workshop at ICLR), 2020.

Jude Oyasor, Mpho Raborife, Pravesh Ranchod. Sentiment Analysis as an Indicator to Evaluate Gender disparity on Sexual Violence Tweets in South Africa. International SAUPEC/RobMech/PRASA Conference, 2020.

Kimessha Paupamah, Steven James, Richard Klein. Quantisation and Pruning for Neural Network Compression and Regularisation. International SAUPEC/RobMech/PRASA Conference, 2020.

Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod. Learning Options from Demonstration using Skill Segmentation. International SAUPEC/RobMech/PRASA Conference, 2020.

Nishai Kooverjee, Steven James, Terence Van Zyl. Inter-and Intra-domain Knowledge Transfer for Related Tasks in Deep Character Recognition. International SAUPEC/RobMech/PRASA Conference, 2020.

Pierce Burke, Richard Klein. Confident in the Crowd: Bayesian Inference to Improve Data Labelling in Crowdsourcing. International SAUPEC/RobMech/PRASA Conference, 2020.

Matthew Reynard, Herman Kamper, Herman A Engelbrecht, Benjamin Rosman. Combining Primitive DQNs for Improved Reinforcement Learning in Minecraft. International SAUPEC/RobMech/PRASA Conference, 2020.

Edward Boje, Ross Christopher, John Fernandes, James Hepworth, Rangith Kuriakose, Karel Kruger, Trevor Lorimer, Nicolaas Luwes, Hennie Mouton, Amir Patel, Benjamin Rosman, Willie Smit, Riaan Stopforth, Beatrice van Eden, Theo van Niekerk, Herman Vermaak, Daniel Withey. A Review of Robotics Research in South Africa. R&D Journal of the South African Institution of Mechanical Engineering, 2019.

Perusha Moodley, Benjamin Rosman, Xia Hong. Understanding Structure of Concurrent Actions. International Conference on Innovative Techniques and Applications of Artificial Intelligence, 2019.

Orhan Can Görür, Benjamin Rosman, Sahin Albayrak. Anticipatory Bayesian Policy Selection for Online Adaptation of Collaborative Robots to Unknown Human Types. International Conference on Autonomous Agents and Multiagent Systems, 2019.

Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman. Composing Value Functions in Reinforcement Learning. International Conference on Machine Learning, 2019.

Craig Bester, Steven James, George Konidaris. Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces. Technical Report, 2019.

Ndivhuwo Makondo, Benjamin Rosman. Towards Improving Incremental Learning of Manipulator Kinematics with Inter-robot Knowledge Transfer. SAUPEC/ROBMECH/PRASA International Conference, 2019.

Beatrice van Eden, Benjamin Rosman. An Overview of Robot Vision. SAUPEC/ROBMECH/PRASA International Conference, 2019.

Dhruv Bhugwan, Pravesh Ranchod, Richard Klein, Benjamin Rosman. A Comparison Between Fully Connected and Deconvolutional Layers for Road Segmentation from Satellite Imagery. SAUPEC/ROBMECH/PRASA International Conference, 2019.

Ofir Marom, Benjamin Rosman. Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning. Advances in Neural Information Processing Systems, 2018.

Abdallah Bashir, Abubakr Hassan, Benjamin Rosman, Daniel Duma, Mohanad Ahmed. Implementation of a Neural Natural Language Understanding Component for Arabic Dialogue Systems. 4th International Conference on Arabic Computational Linguistics, 2018.

Richard Fisher, Benjamin Rosman, Vladimir Ivan. Real-time Motion Planning in Changing Environments Using Topology-based Encoding of Past Knowledge. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018.

Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter. Symbol Emergence in Cognitive Developmental Systems: A Survey. IEEE Transactions on Cognitive and Developmental Systems, 2018.

Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman. Will it Blend? Composing Value Functions in Reinforcement Learning. The 2nd Lifelong Learning: A Reinforcement Learning Approach (LLARLA) Workshop @ FAIM, 2018.

Steven James, Benjamin Rosman, George Konidaris. Learning to Plan with Portable Symbols. ICML/IJCAI/AAMAS 2018 Workshop on Planning and Learning, 2018.

Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa. Accelerating Model Learning with Inter-robot Knowledge Transfer. IEEE International Conference on Robotics and Automation, 2018.

Adam Earle, Andrew Saxe, Benjamin Rosman. Hierarchical Subtask Discovery with Non-negative Matrix Factorization. Proceedings of the Sixth International Conference on Learning Representations, 2018.

Orhan Can Görür, Benjamin Rosman, Fikret Sivrikaya, Sahin Albayrak. Social Cobots: Anticipatory Decision-Making for Collaborative Robots Incorporating Unexpected Human Behaviors. ACM/IEEE International Conference on Human-Robot Interaction, 2018.

Ritesh Ajoodha, Benjamin Rosman. Learning the Influence Structure between Partially Observed Stochastic Processes using IoT Sensor Data. SmartIoT: AI Enhanced IoT Data Processing for Intelligent Applications at AAAI-18, 2018.

Ofir Marom, Benjamin Rosman. Belief Reward Shaping in Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2018.

Ndivhuwo Makondo, Michihisa Hiratsuka, Benjamin Rosman, Osamu Hasegawa. A Non-linear Manifold Alignment Approach to Robot Learning from Demonstrations. Journal of Robotics and Mechatronics, 2018.

Ritesh Ajoodha, Benjamin Rosman. Tracking Influence between Naïve Bayes Models using Score-Based Structure Learning. PRASA-RobMech International Conference, 2017.

Jason Perlow, Benjamin Rosman, Bradley Hayes, Pravesh Ranchod. Raw Material Selection for Object Construction. PRASA-RobMech International Conference, 2017.

Luke Darlow, Benjamin Rosman. Fingerprint Minutiae Extraction using Deep Learning. International Joint Conference on Biometrics, 2017.

Benjamin van Niekerk, Andreas Damianou, Benjamin Rosman. Online Constrained Model-based Reinforcement Learning. Conference on Uncertainty in Artificial Intelligence, 2017.

Andrew Saxe, Adam Earle, Benjamin Rosman. Hierarchy Through Composition with Multitask LMDPs. International Conference on Machine Learning, 2017.

Adam Earle, Andrew Saxe, Benjamin Rosman. Hierarchical Subtask Discovery with Non-negative Matrix Factorization. Workshop on Lifelong Learning: A Reinforcement Learning Approach at ICML, 2017.

Orhan Can Görür, Benjamin Rosman, Guy Hoffman, Sahin Albayrak. Toward Integrating Theory of Mind into Adaptive Decision-Making of Social Robots to Understand Human Intention. Workshop on the Role of Intentions in Human-Robot Interaction, 2017.

Steven James, George Konidaris, Benjamin Rosman. An Analysis of Monte Carlo Tree Search. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017.

Robert Berman, Richardt Benade, Benjamin Rosman, Paul Nordengen. Predicting High-speed Performance of a B-Double. Fourteenth International Symposium on Heavy Vehicle Transport Technology, 2016.

Michihisa Hiratsuka, Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa. Trajectory Learning from Human Demonstrations via Manifold Mapping. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016.

Steven James, Benjamin Rosman, George Konidaris. An Investigation into the Effectiveness of Heavy Rollouts in UCT. General Intelligence in Game-Playing Agents Workshop at IJCAI, 2016.

Pablo Hernandez-Leal, Benjamin Rosman, Matthew Taylor, L Enrique Sucar, Enrique Munoz de Cote. A Bayesian approach for Learning and Tracking Switching, Non-stationary Opponents. Autonomous Agents and Multiagent Systems, 2016.

Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy. Bayesian Policy Reuse. Machine Learning Journal, 2016.

Warwick Masson, Pravesh Ranchod, George Konidaris. Reinforcement Learning with Parameterized Actions. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.

Pablo Hernandez-Leal, Matthew Taylor, Benjamin Rosman, L Enrique Sucar, Enrique Munoz de Cote. Identifying and Tracking Switching, Non-stationary Opponents: a Bayesian Approach. Workshop on Multiagent Interaction without Prior Coordination at AAAI, 2016.

Ritesh Ajoodha, Richard Klein, Benjamin Rosman. Single-labelled Music Genre Classification Using Content-Based Features. PRASA-RobMech International Conference, 2015.

Robert Berman, Richardt Benade, Benjamin Rosman. Autonomous Prediction of Performance-based Standards for Heavy Vehicles. PRASA-RobMech International Conference, 2015.

Ndivhuwo Makondo, Benjamin Rosman, Osamu Hasegawa. Knowledge Transfer for Learning Robot Models via Local Procrustes Analysis. IEEE-RAS International Conference on Humanoid Robots, 2015.

Pravesh Ranchod, Benjamin Rosman, George Konidaris. Nonparametric Bayesian Reward Segmentation for Skill Discovery Using Inverse Reinforcement Learning. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2015.

Benjamin Rosman, Bradley Hayes, Brian Scassellati. Enhancing Agent Safety through Autonomous Environment Adaptation. Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, 2015.

Benjamin Rosman, Subramanian Ramamoorthy. Action Priors for Learning Domain Invariances. IEEE Transactions on Autonomous Mental Development, 2015.

Ashley Kleinhans, Benjamin Rosman, Michael Michalik, Bryan Tripp, Renaud Detry. G3DB: A Database of Successful and Failed Grasps with RGB-D Images, Point Clouds, Mesh Models and Gripper Parameters. Workshop on Robotic Hands, Grasping, and Manipulation at ICRA, 2015.

Benjamin Rosman. Context-based Online Policy Instantiation for Multiple Tasks and Changing Environments. Proceedings of the 2014 PRASA, RobMech and AfLaT International Joint Symposium, 2014.

Beatrice van Eden, Benjamin Rosman, Daniel Withey, Terence Ratshidaho, Mogomotsi Keaikitse, Ditebogo Masha, Ashley Kleinhans, Ahmed Shaik. CHAMP: A Bespoke Integrated System for Mobile Manipulation. Proceedings of the 2014 PRASA, RobMech and AfLaT International Joint Symposium, 2014.

Benjamin Rosman. Behavioural Domain Knowledge Transfer for Autonomous Agents. AAAI Fall Symposium on Knowledge, Skill, and Behavior Transfer in Autonomous Robots, 2014.

Benjamin Rosman. Feature Selection for Domain Knowledge Representation through Multitask Learning. IEEE International Conference on Development and Learning and on Epigenetic Robotics, 2014.

Ashley Kleinhans, Serge Thill, Benjamin Rosman, Renaud Detry, Bryan Tripp. Modelling Primate Control of Grasping for Robotics Applications. Second Workshop on Affordances: Visual Perception of Affordances and Functional Visual Primitives for Scene Analysis, 2014.

MM Hassan Mahmud, Benjamin Rosman, Subramanian Ramamoorthy, Pushmeet Kohli. Adapting Interaction Environments to Diverse Users through Online Action Set Selection. AAAI Workshop on Machine Learning for Interactive Systems, 2014.

Benjamin Rosman, Subramanian Ramamoorthy. Giving Advice to Agents with Hidden Goals. IEEE International Conference on Robotics and Automation, 2014.

Benjamin Rosman, Subramanian Ramamoorthy, MM Hassan Mahmud, Pushmeet Kohli. On User Behaviour Adaptation Under Interface Change. International Conference on Intelligent User Interfaces, 2014.

Subramanian Ramamoorthy, MM Hassan Mahmud, Benjamin Rosman, Pushmeet Kohli. Latent-variable MDP models for adapting the interaction environment of diverse users. Tech. Rep., 2013.

MM Hassan Mahmud, Majd Hawasly, Benjamin Rosman, Subramanian Ramamoorthy. Clustering Markov Decision Processes For Continual Transfer. arXiv e-prints, 2013.

MM Mahmud, Majd Hawasly, Benjamin Rosman, Subramanian Ramamoorthy. Clustering markov decision processes for continual transfer. arXiv preprint arXiv:1311.3959, 2013.

Benjamin Rosman, Subramanian Ramamoorthy. What Good are Actions? Accelerating Learning using Learned Action Priors. IEEE International Conference on Development and Learning and on Epigenetic Robotics, 2012.

Benjamin Rosman, Subramanian Ramamoorthy. A Multitask Representation using Reusable Local Policy Templates. AAAI Spring Symposium Series on Designing Intelligent Robots: Reintegrating AI, 2012.

Benjamin Rosman, Subramanian Ramamoorthy. Learning Spatial Relationships between Objects. International Journal of Robotics Research, 2011.

Benjamin Rosman, Subramanian Ramamoorthy. A Game Theoretic Procedure for Learning Hierarchically Structured Strategies. IEEE International Conference on Robotics and Automation, 2010.

Sarah Rauchas, Benjamin Rosman, George Konidaris, Ian Sanders. Language Performance at High School and Success in First Year Computer Science. SIGCSE Technical Symposium on Computer Science Education, 2006.