Benjamin Rosman

发表

Hierarchy Through Composition with Multitask LMDPs

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2017, ICML.

Symbol Emergence in Cognitive Developmental Systems: A Survey

Florentin Wörgötter, Takayuki Nagai, Emre Ugur, 2018, IEEE Transactions on Cognitive and Developmental Systems.

A Boolean Task Algebra for Reinforcement Learning

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2020, NeurIPS.

Explorer Bayesian Policy Reuse

Benjamin Rosman, Majd Hawasly, 2017 .

Learning to Plan with Portable Symbols

G. Konidaris, Benjamin Rosman, Steven James, 2018 .

Game-Theoretic Procedures for Learning Structured Strategies from Demonstration

Benjamin Rosman, 2009 .

Logical Composition for Lifelong Reinforcement Learning

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2020 .

Single-labelled music genre classification using content-based features

Benjamin Rosman, Ritesh Ajoodha, Richard Klein, 2015, 2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech).

Sign Object Interpretant Symbol Reference ( Signifier ) Referent ( Signified ) “ Apple ”

F. Wörgötter, Benjamin Rosman, J. Piater, 2018 .

World Value Functions: Knowledge Representation for Multitask Reinforcement Learning

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2022, arXiv.org.

Skill Machines: Temporal Logic Composition in Reinforcement Learning

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2022, ArXiv.

Designing intelligent robots : reintegrating AI : papers from the AAAI Spring Symposium

Byron Boots, George Konidaris, Benjamin Rosman, 2012 .

World Value Functions: Knowledge Representation for Learning and Planning

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2022, ArXiv.

G ENERALISATION IN L IFELONG R EINFORCEMENT L EARNING THROUGH L OGICAL C OMPOSITION

Geraud Nangue Tasse, Benjamin Rosman, Steven James, 2021 .

Learning Abstract and Transferable Representations for Planning

G. Konidaris, Benjamin Rosman, Steven James, 2022, ArXiv.

The challenge of redundancy on multi-agent value factorisation

Benjamin Rosman, Siddarth S. Singh, 2023, AAMAS.

A UTONOMOUS L EARNING OF O BJECT -C ENTRIC A BSTRACTIONS FOR H IGH -L EVEL P LANNING

Benjamin Rosman, Steven James, Steven D. James, 2022 .

Play-style Identification through Deep Unsupervised Clustering of Trajectories

Benjamin Rosman, Richard Klein, Branden Ingram, 2022, 2022 IEEE Conference on Games (CoG).

Improved Action Prediction through Multiple Model Processing of Player Trajectories

Benjamin Rosman, Richard Klein, Branden Ingram, 2022, 2022 IEEE Conference on Games (CoG).

Learning Object-Centric Representations for High-Level Planning in Minecraft

G. Konidaris, Benjamin Rosman, Steven James, 2020 .

Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules

Benjamin Rosman, Sara Hooker, Arnu Pretorius, 2022 .

Comparing Synthetic Tabular Data Generation Between a Probabilistic Model and a Deep Learning Model for Education Use Cases

Benjamin Rosman, Vukosi Marivate, H. Combrink, 2022, ArXiv.

Reinforcement Learning in Education: A Multi-Armed Bandit Approach

Benjamin Rosman, Vukosi Marivate, H. Combrink, 2022, ArXiv.

Applying a principle of explicability to AI research in Africa: should we do it?

Benjamin Rosman, Mary Carman, Benjamin Rosman, 2020, Ethics and Information Technology.

Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization pdf

Benjamin Rosman, Sara Hooker, Kale-ab Tessera, 2021, ArXiv.

Reasoning about Unforeseen Possibilities During Policy Learning pdf

Alex Lascarides, Benjamin Rosman, Subramanian Ramamoorthy, 2018, ArXiv.

Applying a principle of explicability to AI research in Africa: should we do it?

Benjamin Rosman, M. Carman, 2020, Ethics and Information Technology.

A game-theoretic procedure for learning hierarchically structured strategies

Benjamin Rosman, Subramanian Ramamoorthy, S. Ramamoorthy, 2010, 2010 IEEE International Conference on Robotics and Automation.

Learning domain abstractions for long lived robots

Benjamin Saul Rosman, Benjamin Rosman, 2014 .

What good are actions? Accelerating learning using learned action priors

Benjamin Rosman, Subramanian Ramamoorthy, S. Ramamoorthy, 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

Learning spatial relationships between objects

Benjamin Rosman, Subramanian Ramamoorthy, S. Ramamoorthy, 2011, Int. J. Robotics Res..

Deep Reinforcement Learning for Robotic Hand Manipulation

Benjamin Rosman, M. Saeed, Mohammed Nagdi, 2021, 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE).

Fairness and accountability of AI in disaster risk management: Opportunities and challenges

Robert Soden, Benjamin Rosman, Yola Georgiadou, 2021, Patterns.

Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning

Pravesh Ranchod, George Konidaris, Benjamin Rosman, 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

A Non-Linear Manifold Alignment Approach to Robot Learning from Demonstrations

Benjamin Rosman, Osamu Hasegawa, Ndivhuwo Makondo, 2018, J. Robotics Mechatronics.

Trajectory learning from human demonstrations via manifold mapping

Benjamin Rosman, Osamu Hasegawa, Ndivhuwo Makondo, 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Towards improving incremental learning of manipulator kinematics with inter-robot knowledge transfer

Benjamin Rosman, Ndivhuwo Makondo, Benjamin Rosman, 2019, 2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA).

Action Priors for Learning Domain Invariances

Benjamin Rosman, Subramanian Ramamoorthy, S. Ramamoorthy, 2015, IEEE Transactions on Autonomous Mental Development.

Behavioural Domain Knowledge Transfer for Autonomous Agents

Benjamin Rosman, Benjamin Rosman, 2014, AAAI Fall Symposia.

Learning Portable Representations for High-Level Planning

George Konidaris, Benjamin Rosman, Steven James, 2019, ICML.

A Remote Sensing Method to Monitor Water, Aquatic Vegetation, and Invasive Water Hyacinth at National Extents

Benjamin Rosman, Geethen Singh, Chevonne Reynolds, 2020, Remote. Sens..

Clustering Markov Decision Processes For Continual Transfer pdf

M. M. Hassan Mahmud, Benjamin Rosman, Subramanian Ramamoorthy, 2013, ArXiv.

FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation pdf

Sahin Albayrak, Fikret Sivrikaya, Benjamin Rosman, 2021, ACM Transactions on Human-Robot Interaction.

Giving advice to agents with hidden goals

Benjamin Rosman, Subramanian Ramamoorthy, S. Ramamoorthy, 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

G. Konidaris, Benjamin Rosman, Steven D. James, 2022, ICLR.

Analyzing Reinforcement Learning Algorithms for Nitrogen Fertilizer Management in Simulated Crop Growth

Benjamin Rosman, Michael Vogt, 2022, EPiC Series in Computing.

Hierarchically Composing Level Generators for the Creation of Complex Structures

Benjamin Rosman, Michael Beukman, Branden Ingram, 2023, ArXiv.

Accelerating Model Learning with Inter-Robot Knowledge Transfer

Benjamin Rosman, Osamu Hasegawa, Ndivhuwo Makondo, 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

An Analysis of Monte Carlo Tree Search

George Konidaris, Benjamin Rosman, Steven James, 2017, AAAI.

Context-based online policy instantiation for multiple tasks and changing environments

Benjamin Rosman, Benjamin Rosman, 2014 .

Identifying and Tracking Switching, Non-Stationary Opponents: A Bayesian Approach

Matthew E. Taylor, Pablo Hernandez-Leal, Luis Enrique Sucar, 2016, AAAI Workshop: Multiagent Interaction without Prior Coordination.

Should I Trust You? Incorporating Unreliable Expert Advice in Human-Agent Interaction

Benjamin Rosman, Ritesh Ajoodha, Tamlin Love, 2021 .

Modelling Primate Control of Grasping for Robotics Applications

Benjamin Rosman, Serge Thill, Renaud Detry, 2014, ECCV Workshops.

Toward integrating Theory of Mind into adaptive decision-making of social robots to understand human intention

Sahin Albayrak, Benjamin Rosman, Benjamin Rosman, 2017 .

Utilising Uncertainty for Efficient Learning of Likely-Admissible Heuristics

Ofir Marom, Benjamin Rosman, Benjamin Rosman, 2020, ICAPS.

Reducing the Planning Horizon Through Reinforcement Learning

Benjamin Rosman, A. Cohn, M. Leonetti, 2022, ECML/PKDD.

Learning to Follow Language Instructions with Compositional Policies pdf

Benjamin Rosman, Matthew Gombolay, Nakul Gopalan, 2021, ArXiv.

Composing Value Functions in Reinforcement Learning

Benjamin Rosman, Benjamin van Niekerk, Adam Christopher Earle, 2019, ICML.

Social Cobots: Anticipatory Decision-Making for Collaborative Robots Incorporating Unexpected Human Behaviors

Sahin Albayrak, Fikret Sivrikaya, Benjamin Rosman, 2018, 2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

Autonomous prediction of performance-based standards for heavy vehicles

Benjamin Rosman, Robert Berman, Richardt Benade, 2015, 2015 Pattern Recognition Association of South Africa and Robotics and Mechatronics International Conference (PRASA-RobMech).

Belief Reward Shaping in Reinforcement Learning

Ofir Marom, Benjamin Rosman, Benjamin Rosman, 2018, AAAI.

Online Constrained Model-based Reinforcement Learning pdf

Benjamin Rosman, Benjamin van Niekerk, Andreas C. Damianou, 2017, UAI.

On The Specialization of Neural Modules

Andrew M. Saxe, Benjamin Rosman, Richard Klein, 2023, ICLR.

Symbol Emergence in Cognitive Developmental Systems: A Survey

F. Wörgötter, Benjamin Rosman, J. Piater, 2018, IEEE Transactions on Cognitive and Developmental Systems.

If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks pdf

Benjamin Rosman, Steve Kroon, Ryan Eloff, 2019, Pattern Recognit. Lett..

Generalisation in Lifelong Reinforcement Learning through Logical Composition

Geraud Nangue Tasse, Benjamin Rosman, Steven D. James, 2022, International Conference on Learning Representations.

Hierarchically Composing Level Generators for the Creation of Complex Structures

Benjamin Rosman, Michael Beukman, Branden Ingram, 2023, IEEE Transactions on Games.

Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks pdf

Vered Aharonson, Benjamin Rosman, David M Rubin, 2019, Informatics in Medicine Unlocked.

Bayesian policy reuse

Benjamin Rosman, Subramanian Ramamoorthy, Majd Hawasly, 2015, Machine Learning.

Combining primitive DQNs for improved reinforcement learning in Minecraft

Benjamin Rosman, Herman Kamper, Herman A. Engelbrecht, 2020, 2020 International SAUPEC/RobMech/PRASA Conference.

Hierarchical Subtask Discovery With Non-Negative Matrix Factorization pdf

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2017, ICLR.

Hierarchy through Composition with Linearly Solvable Markov Decision Processes pdf

Benjamin Rosman, Andrew M. Saxe, Adam Christopher Earle, 2016, ArXiv.

Knowledge Transfer using Model-Based Deep Reinforcement Learning

Benjamin Rosman, Ndivhuwo Makondo, Tlou Boloka, 2021, 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA).

Learning the Influence Structure between Partially Observed Stochastic Processes Using IoT Sensor Data

Benjamin Rosman, Ritesh Ajoodha, Benjamin Rosman, 2018, AAAI Workshops.

Raw material selection for object construction

Pravesh Ranchod, Bradley Hayes, Benjamin Rosman, 2017, 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech).

An overview of robot vision

Benjamin Rosman, Beatrice van Eden, Benjamin Rosman, 2019, 2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA).

Who should I trust? Cautiously learning with unreliable experts

Benjamin Rosman, Ritesh Ajoodha, Tamlin Love, 2022, Neural Computing and Applications.

Discovery of Influence between Processes Represented by Hidden Markov Models

Benjamin Rosman, Ritesh Ajoodha, Benjamin Rosman, 2020, 2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS).

Latent-Variable MDP Models for Adapting the Interaction Environment of Diverse Users

Pushmeet Kohli, M. M. Hassan Mahmud, Ram Ramamoorthy, 2014 .

FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation

Benjamin Rosman, S. Albayrak, F. Sivrikaya, 2021, ACM Transactions on Human-Robot Interaction.

On user behaviour adaptation under interface change

Pushmeet Kohli, M. M. Hassan Mahmud, Benjamin Rosman, 2014, IUI.

Anticipatory Bayesian Policy Selection for Online Adaptation of Collaborative Robots to Unknown Human Types

Sahin Albayrak, Benjamin Rosman, O. Can Görür, 2019, AAMAS.