Sequoia: A Software Framework to Unify Continual Learning Research
By Fabrice Normandin, Florian Golemo, Oleksiy Ostapenko, Pau Rodr'iguez L'opez, Matthew Riemer, Julio Hurtado, Khimya Khetarpal, Dominic Zhao, Ryan Lindeborg, Timothée Lesort and 3 more. 2021
25 citations recorded by the source corpus.
The field of Continual Learning (CL) seeks to develop algorithms that accumulate knowledge and skills over time through interaction with non-stationary environments. In practice, a plethora of evaluation procedures (settings) and algorithmic solutions (methods) exist, each with their own potentially disjoint set of assumptions. This variety makes measuring progress in CL difficult. We propose a taxonomy of settings, where each setting is described as a set of assumptions. A tree-shaped hierarchy emerges from this view, where more general settings become the parents of those with more restrictive assumptions. This makes it possible to use inheritance to share and reuse research, as developing a method for a given setting also makes it directly applicable onto any of its children. We instantiate this idea as a publicly available software framework called Sequoia, which features a wide variety of settings from both the Continual Supervised Learning (CSL) and Continual Reinforcement Learning (CRL) domains. Sequoia also includes a growing suite of methods which are easy to extend and customize, in addition to more specialized methods from external libraries. We hope that this new paradigm and its first implementation can help unify and accelerate research in CL. You can help us grow the tree by visiting www.github.com/lebrice/Sequoia.
Subfields: Epidemiology, Infectious Diseases
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Epidemiology
In Infectious Diseases
Citations in the corpus
- Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, background): “The variable z is often referred to as a task (or context) (Caccia et al., 2020; Normandin et al., 2021).”
- Continual Learning via Local Module Composition (2021, background): “The rapid growth of continual learning has lead researchers to work on empirical studies [20, 58, 56], surveys [32, 42, 55, 66, 67] as well as CL-specific software [72, 22, 59].”
- CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability (2021, methodology): “Software for replication: Finally, for the sake of completeness, we also mention that there exist recent propositions for continual learning software tools, such as the Avalanche (Lomonaco et al., 2021) and Sequoia (Normandin et al., 2021) libraries on top of the popular machine learning framework P”
- CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, methodology): “The most complex environments that Sequoia uses are Meta-World, with simple state-based manipulation tasks, and MonsterKong, composed of 8 hand-designed platformer levels.”