Follow
Steven James
Title
Cited by
Cited by
Year
An Analysis of Monte Carlo Tree Search
S James, G Konidaris, B Rosman
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence …, 2017
462017
Learning Portable Representations for High-Level Planning
S James, B Rosman, G Konidaris
International Conference on Machine Learning, 2020
33*2020
Composing value functions in reinforcement learning
B Van Niekerk, S James, A Earle, B Rosman
International conference on machine learning, 6401-6409, 2019
30*2019
Multi-pass Q-networks for deep reinforcement learning with parameterised action spaces
CJ Bester, SD James, GD Konidaris
arXiv preprint arXiv:1905.04388, 2019
242019
A Boolean Task Algebra for Reinforcement Learning
G Nangue Tasse, S James, B Rosman
Advances in Neural Information Processing Systems 33, 2020
212020
Quantisation and Pruning for Neural Network Compression and Regularisation
K Paupamah, S James, R Klein
2020 International SAUPEC/RobMech/PRASA Conference, 1-6, 2020
192020
Inter-and intra-domain knowledge transfer for related tasks in deep character recognition
N Kooverjee, S James, T Van Zyl
2020 International SAUPEC/RobMech/PRASA Conference, 1-6, 2020
62020
Generalisation in Lifelong Reinforcement Learning through Logical Composition
G Nangue Tasse, S James, B Rosman
International Conference on Learning Representations, 2022
5*2022
Autonomous Learning of Object-Centric Abstractions for High-Level Planning
S James, B Rosman, G Konidaris
International Conference on Learning Representations, 2022
4*2022
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
A Pretorius, E Van Biljon, B van Niekerk, R Eloff, M Reynard, S James, ...
Pattern Recognition Letters 138, 95-105, 2020
22020
Learning Options from Demonstration using Skill Segmentation
M Cockcroft, S Mawjee, S James, P Ranchod
2020 International SAUPEC/RobMech/PRASA Conference, 1-6, 2020
22020
The Effect of Simulation Bias on Action Selection in Monte Carlo Tree Search
SD James
University of the Witwatersrand, 2016
22016
An Investigation into the Effectiveness of Heavy Rollouts in UCT
S James, B Rosman, G Konidaris
The IJCAI-16 Workshop on General Game Playing, 55 - 61, 2016
22016
World Value Functions: Knowledge Representation for Multitask Reinforcement Learning
G Nangue Tasse, S James, B Rosman
The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision …, 2022
12022
Combining Evolutionary Search with Behaviour Cloning for Procedurally Generated Content
N Muir, S James
Proceedings of 43rd Conference of the South African Institute for Computer …, 2022
2022
World Value Functions: Knowledge Representation for Learning and Planning
G Nangue Tasse, B Rosman, S James
Bridging the Gap Between AI Planning and Reinforcement Learning Workshop at …, 2022
2022
Skill Machines: Temporal Logic Composition in Reinforcement Learning
G Nangue Tasse, D Jarvis, S James, B Rosman
arXiv preprint arXiv:2205.12532, 2022
2022
Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
N Michlo, D Jarvis, R Klein, S James
The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision …, 2022
2022
Learning Abstract and Transferable Representations for Planning
S James, B Rosman, G Konidaris
The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision …, 2022
2022
Adaptive Online Value Function Approximation with Wavelets
M Beukman, M Mitchley, D Wookey, S James, G Konidaris
The 5th Multi-disciplinary Conference on Reinforcement Learning and Decision …, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–20