1 code implementation • 28 Aug 2023 • Colin Bellinger, Laurence Lamarche-Cliche
The report describes the reinforcement learning environments created to facilitate policy learning with the UR10e, a robotic arm from Universal Robots, and presents our initial results in training deep Q-learning and proximal policy optimization agents on the developed reinforcement learning environments.
1 code implementation • 5 Jul 2023 • Colin Bellinger, Mark Crowley, Isaac Tamblyn
The action-perception cycle in RL, however, generally assumes that a measurement of the state of the environment is available at each time step without a cost.
no code implementations • 23 May 2023 • Chris Beeler, Sriram Ganapathi Subramanian, Kyle Sprague, Nouha Chatti, Colin Bellinger, Mitchell Shahen, Nicholas Paquin, Mark Baula, Amanuel Dawit, Zihan Yang, Xinkai Li, Mark Crowley, Isaac Tamblyn
This paper provides a simulated laboratory for making use of Reinforcement Learning (RL) for chemical discovery.
no code implementations • 13 Mar 2023 • Payam Parvizi, Runnan Zou, Colin Bellinger, Ross Cheriton, Davide Spinello
We propose the use of reinforcement learning (RL) to reduce the latency, size and cost of the system by up to $30-40\%$ by learning a control policy through interactions with a low-cost quadrant photodiode rather than a wavefront phase profiling camera.
1 code implementation • 15 Dec 2022 • Damien A. Dablain, Colin Bellinger, Bartosz Krawczyk, David W. Aha, Nitesh V. Chawla
We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance.
no code implementations • 17 Oct 2022 • Damien Dablain, Kristen N. Jacobson, Colin Bellinger, Mark Roberts, Nitesh Chawla
To demystify CNN decisions on imbalanced data, we focus on their latent features.
1 code implementation • 13 Jul 2022 • Damien Dablain, Colin Bellinger, Bartosz Krawczyk, Nitesh Chawla
We empirically study a convolutional neural network's internal representation of imbalanced image data and measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes.
no code implementations • 5 May 2022 • Vitor Cerqueira, Luis Torgo, Paula Branco, Colin Bellinger
The main contribution of our work is a new method called ICLL for tackling IBC tasks which is not based on resampling training observations.
no code implementations • 29 Dec 2021 • Chris Beeler, Xinkai Li, Colin Bellinger, Mark Crowley, Maia Fraser, Isaac Tamblyn
Using a novel toy nautical navigation environment, we show that dynamic programming can be used when only incomplete information about a partially observed Markov decision process (POMDP) is known.
no code implementations • 14 Dec 2021 • Colin Bellinger, Andriy Drozdyuk, Mark Crowley, Isaac Tamblyn
The use of reinforcement learning (RL) in scientific applications, such as materials design and automated chemistry, is increasing.
1 code implementation • 29 Jul 2021 • Kushankur Ghosh, Colin Bellinger, Roberto Corizzo, Bartosz Krawczyk, Nathalie Japkowicz
Structural concept complexity, class overlap, and data scarcity are some of the most important factors influencing the performance of classifiers under class imbalance conditions.
1 code implementation • 9 May 2021 • Michał Koziarski, Colin Bellinger, Michał Woźniak
Our $5\times2$ cross-validated results on 57 benchmark binary datasets with 9 classifiers show that RB-CCR achieves a better precision-recall trade-off than CCR and generally out-performs the state-of-the-art resampling methods in terms of AUC and G-mean.
no code implementations • 3 Dec 2020 • Colin Bellinger, Roberto Corizzo, Nathalie Japkowicz
Class imbalance is a problem of significant importance in applied deep learning where trained models are exploited for decision support and automated decisions in critical areas such as health and medicine, transportation, and finance.
no code implementations • 26 May 2020 • Colin Bellinger, Rory Coles, Mark Crowley, Isaac Tamblyn
Our empirical evaluation demonstrates that Amrl-Q agents are able to learn a policy and state estimator in parallel during online training.
1 code implementation • 15 Apr 2020 • Colin Bellinger, Rory Coles, Mark Crowley, Isaac Tamblyn
Reinforcement learning (RL) has been demonstrated to have great potential in many applications of scientific discovery and design.