no code implementations • ICML 2020 • Ashley Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski
In this paper, we introduce a novel form of a value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
no code implementations • 18 May 2023 • Samuel Schmidgall, Jascha Achterberg, Thomas Miconi, Louis Kirsch, Rojin Ziaei, S. Pardis Hajiseyedrazi, Jason Eshraghian
Artificial neural networks (ANNs) have emerged as an essential tool in machine learning, achieving remarkable success across diverse domains, including image and speech generation, game playing, and robotics.
1 code implementation • 11 Feb 2023 • Thomas Miconi
The parametrization allows us to randomly generate an arbitrary number of novel simple meta-learning tasks.
1 code implementation • 16 Dec 2021 • Thomas Miconi
A hallmark of intelligence is the ability to autonomously learn new flexible, cognitive behaviors - that is, behaviors where the appropriate action depends not just on immediate stimuli (as in simple reflexive stimulus-response associations), but on contextual information that must be adequately acquired, stored and processed for each new instance of the task.
1 code implementation • 4 Jul 2021 • Thomas Miconi
Deep learning networks generally use non-biological learning methods.
no code implementations • 30 Jun 2020 • Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor
Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge.
no code implementations • ICLR 2019 • Thomas Miconi, Aditya Rawal, Jeff Clune, Kenneth O. Stanley
We show that neuromodulated plasticity improves the performance of neural networks on both reinforcement learning and supervised learning tasks.
1 code implementation • 21 Feb 2020 • Ashley D. Edwards, Himanshu Sahni, Rosanne Liu, Jane Hung, Ankit Jain, Rui Wang, Adrien Ecoffet, Thomas Miconi, Charles Isbell, Jason Yosinski
In this paper, we introduce a novel form of value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
5 code implementations • 21 Feb 2020 • Shawn Beaulieu, Lapo Frati, Thomas Miconi, Joel Lehman, Kenneth O. Stanley, Jeff Clune, Nick Cheney
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it.
1 code implementation • 18 Oct 2019 • Ted Moskovitz, Rui Wang, Janice Lan, Sanyam Kapoor, Thomas Miconi, Jason Yosinski, Aditya Rawal
Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space. These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence.
no code implementations • 25 Sep 2019 • Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor
Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge.
5 code implementations • ICML 2018 • Thomas Miconi, Jeff Clune, Kenneth O. Stanley
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training?
no code implementations • 5 Jul 2017 • Thomas Miconi
Here we show that, when groups differ in prevalence of the predicted event, several intuitive, reasonable measures of fairness (probability of positive prediction given occurrence or non-occurrence; probability of occurrence given prediction or non-prediction; and ratio of predictions over occurrences for each group) are all mutually exclusive: if one of them is equal among groups, the other two must differ.
1 code implementation • 8 Sep 2016 • Thomas Miconi
As a result, the networks "learn how to learn" in order to solve the problem at hand: the trained networks automatically perform fast learning of unpredictable environmental features during their lifetime, expanding the range of solvable problems.
1 code implementation • 20 Jun 2016 • Thomas Miconi
We test this method on recurrent neural networks applied to simple sequence prediction problems.