The role of lifelong machine learning in bridging the gap between human and machine learning: A scientometric analysis

M Abulaish, NA Wasi, S Sharma - … Reviews: Data Mining and …, 2024 - Wiley Online Library
Due to advancements in data collection, storage, and processing techniques, machine
learning has become a thriving and dominant paradigm. However, one of its main …

Parameterizing branch-and-bound search trees to learn branching policies

G Zarpellon, J Jo, A Lodi, Y Bengio - … of the aaai conference on artificial …, 2021 - ojs.aaai.org
Abstract Branch and Bound (B&B) is the exact tree search method typically used to solve
Mixed-Integer Linear Programming problems (MILPs). Learning branching policies for MILP …

Approximate information state for approximate planning and reinforcement learning in partially observed systems

J Subramanian, A Sinha, R Seraj, A Mahajan - Journal of Machine …, 2022 - jmlr.org
We propose a theoretical framework for approximate planning and learning in partially
observed systems. Our framework is based on the fundamental notion of information state …

Sequoia: A software framework to unify continual learning research

F Normandin, F Golemo, O Ostapenko… - arxiv preprint arxiv …, 2021 - arxiv.org
The field of Continual Learning (CL) seeks to develop algorithms that accumulate
knowledge and skills over time through interaction with non-stationary environments. In …

Structured cooperative reinforcement learning with time-varying composite action space

W Li, X Wang, B **, D Luo… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In recent years, reinforcement learning has achieved excellent results in low-dimensional
static action spaces such as games and simple robotics. However, the action space is …

In-context reinforcement learning for variable action spaces

V Sinii, A Nikulin, V Kurenkov, I Zisman… - arxiv preprint arxiv …, 2023 - arxiv.org
Recent work has shown that supervised pre-training on learning histories of RL algorithms
results in a model that captures the learning process and is able to improve in-context on …

Rewiring neurons in non-stationary environments

Z Sun, Y Mu - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
The human brain rewires itself for neuroplasticity in the presence of new tasks. We are
inspired to harness this key process in continual reinforcement learning, prioritizing …