Rosman, Benjamin

27 publications

JAIR 2025 Composition and Zero-Shot Transfer with Lattice Structures in Reinforcement Learning Geraud Nangue Tasse, Steven James, Benjamin Rosman

ICLR 2025 Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

NeurIPSW 2024 A Linear Network Theory of Iterated Learning Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

TMLR 2024 Compositional Instruction Following with Language Models and Reinforcement Learning Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Ray Mooney, Benjamin Rosman

ICLR 2024 Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

ICLRW 2023 A Framework for Grassroots Research Collaboration in Machine Learning and Global Health Christopher Brian Currin, Mercy Nyamewaa Asiedu, Chris Fourie, Benjamin Rosman, Houcemeddine Turki, Atnafu Lambebo Tonja, Jade Abbott, Marvellous Ajala, Sadiq Adewale Adedayo, Chris Chinenye Emezue, Daphne Machangara

NeurIPS 2023 Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman

NeurIPSW 2023 Generalisable Agents for Neural Network Optimisation Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan John de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius

NeurIPSW 2023 Generalisable Agents for Neural Network Optimisation Kale-ab Tessera, Callum Rhys Tilbury, Sasha Abramowitz, Ruan John de Kock, Omayma Mahjoub, Benjamin Rosman, Sara Hooker, Arnu Pretorius

ICLR 2023 On the Specialization of Neural Modules Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

ICLR 2022 Autonomous Learning of Object-Centric Abstractions for High-Level Planning Steven James, Benjamin Rosman, George Konidaris

ICLR 2022 Generalisation in Lifelong Reinforcement Learning Through Logical Composition Geraud Nangue Tasse, Steven James, Benjamin Rosman

ECML-PKDD 2022 Reducing the Planning Horizon Through Reinforcement Learning Logan Dunbar, Benjamin Rosman, Anthony G. Cohn, Matteo Leonetti

NeurIPSW 2022 Skill Machines: Temporal Logic Composition in Reinforcement Learning Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

NeurIPSW 2021 Generalisation in Lifelong Reinforcement Learning Through Logical Composition Geraud Nangue Tasse, Steven James, Benjamin Rosman

NeurIPS 2020 A Boolean Task Algebra for Reinforcement Learning Geraud Nangue Tasse, Steven James, Benjamin Rosman

ICML 2020 Learning Portable Representations for High-Level Planning Steven James, Benjamin Rosman, George Konidaris

ICMLW 2020 Logical Composition in Lifelong Reinforcement Learning Geraud Nangue Tasse, Steven James, Benjamin Rosman

ICML 2019 Composing Value Functions in Reinforcement Learning Benjamin Van Niekerk, Steven James, Adam Earle, Benjamin Rosman

AAAI 2018 Belief Reward Shaping in Reinforcement Learning Ofir Marom, Benjamin Rosman

ICLR 2018 Hierarchical Subtask Discovery with Non-Negative Matrix Factorization Adam C. Earle, Andrew M. Saxe, Benjamin Rosman

NeurIPS 2018 Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning Ofir Marom, Benjamin Rosman

AAAI 2017 An Analysis of Monte Carlo Tree Search Steven James, George Dimitri Konidaris, Benjamin Rosman

ICML 2017 Hierarchy Through Composition with Multitask LMDPs Andrew M. Saxe, Adam C. Earle, Benjamin Rosman

UAI 2017 Online Constrained Model-Based Reinforcement Learning Benjamin van Niekerk, Andreas C. Damianou, Benjamin Rosman

MLJ 2016 Bayesian Policy Reuse Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy

ECCVW 2014 Modelling Primate Control of Grasping for Robotics Applications Ashley Kleinhans, Serge Thill, Benjamin Rosman, Renaud Detry, Bryan P. Tripp