Nicholay Topin
Nicholay Topin
Verified email at
Cited by
Cited by
Super-convergence: Very fast training of neural networks using large learning rates
LN Smith, N Topin
Artificial intelligence and machine learning for multi-domain operations …, 2019
MineRL: A Large-Scale Dataset of Minecraft Demonstrations
WH Guss, B Houghton, N Topin, P Wang, C Codel, M Veloso, ...
arXiv preprint arXiv:1907.13440, 2019
Deep convolutional neural network design patterns
LN Smith, N Topin
arXiv preprint arXiv:1611.00847, 2016
The minerl competition on sample efficient reinforcement learning using human priors
WH Guss, C Codel, K Hofmann, B Houghton, N Kuno, S Milani, ...
arXiv preprint arXiv:1904.10079 2, 2019
Generation of Policy-Level Explanations for Reinforcement Learning
N Topin, M Veloso
AAAI 2019, 2019
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
AM Roth, N Topin, P Jamshidi, M Veloso
arXiv preprint arXiv:1907.01180, 2019
Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes.
N Topin, N Haltmeyer, S Squire, J Winder, Marie desJardins, ...
IJCAI, 3856-3864, 2015
Super-convergence: Very fast training of residual networks using large learning rates
LN Smith, N Topin
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
WH Guss, MY Castro, S Devlin, B Houghton, NS Kuno, C Loomis, S Milani, ...
arXiv preprint arXiv:2101.11071, 2021
Retrospective analysis of the 2019 minerl competition on sample efficient reinforcement learning
S Milani, N Topin, B Houghton, WH Guss, SP Mohanty, K Nakata, ...
NeurIPS 2019 Competition and Demonstration Track, 203-214, 2020
Exploring loss function topology with cyclical learning rates
LN Smith, N Topin
arXiv preprint arXiv:1702.04283, 2017
The MineRL BASALT Competition on Learning from Human Feedback
R Shah, C Wild, SH Wang, N Alex, B Houghton, W Guss, S Mohanty, ...
arXiv preprint arXiv:2107.01969, 2021
A Survey of Explainable Reinforcement Learning
S Milani, N Topin, M Veloso, F Fang
arXiv preprint arXiv:2202.08434, 2022
Minerl diamond 2021 competition: Overview, results, and lessons learned
A Kanervisto, S Milani, K Ramanauskas, N Topin, Z Lin, J Li, J Shi, D Ye, ...
NeurIPS 2021 Competitions and Demonstrations Track, 13-28, 2022
Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods
N Topin, S Milani, F Fang, M Veloso
AAAI 2021, 2021
Guaranteeing reproducibility in deep learning competitions
B Houghton, S Milani, N Topin, W Guss, K Hofmann, D Perez-Liebana, ...
arXiv preprint arXiv:2005.06041, 2020
Towards robust and domain agnostic reinforcement learning competitions: MineRL 2020
WH Guss, S Milani, N Topin, B Houghton, S Mohanty, A Melnik, A Harter, ...
NeurIPS 2020 Competition and Demonstration Track, 233-252, 2021
Online planning for autonomous underwater vehicles performing information gathering tasks in large subsea environments
H Yetkin, J McMahon, N Topin, A Wolek, Z Waters, DJ Stilwell
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2019
Use-Case-Grounded Simulations for Explanation Evaluation
V Chen, N Johnson, N Topin, G Plumb, A Talwalkar
arXiv preprint arXiv:2206.02256, 2022
MAVIPER: Learning Decision Tree Policies for Interpretable Multi-Agent Reinforcement Learning
S Milani, Z Zhang, N Topin, ZR Shi, C Kamhoua, EE Papalexakis, F Fang
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2023
The system can't perform the operation now. Try again later.
Articles 1–20