ELLA: An Efficient Lifelong Learning Algorithm - Online Appendix
نویسنده
چکیده
where we use tick marks to denote the updated versions of D(t) and s(t) after receiving the new training data, and D(t) 1 2 is the matrix square-root of D(t). The updates to A consist of adding or subtracting an outer-product of a matrix of size (d × k)-by-d, which implies that each update has rank at most d. If we have already computed the eigenvalue decomposition of the old A, we can compute the eigenvalue decomposition of the updated value of A in O(d3k2) using the recursive decomposition algorithm proposed by Yu (1991). Given the eigenvalue decomposition of the updated value of A = UΣU�, we can compute the new value of L by considering the resulting linear system in canonical form:
منابع مشابه
ELLA: An Efficient Lifelong Learning Algorithm
The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers...
متن کاملScalable Lifelong Learning with Active Task Selection
The recently developed Efficient Lifelong Learning Algorithm (ELLA) acquires knowledge incrementally over a sequence of tasks, learning a repository of latent model components that are sparsely shared between models. ELLA shows strong performance in comparison to other multi-task learning algorithms, achieving nearly identical performance to batch multi-task learning methods while learning task...
متن کاملRobotic Search & Rescue via Online Multi-task Reinforcement Learning
Reinforcement learning (RL) is a general and well-known method that a robot can use to learn an optimal control policy to solve a particular task. We would like to build a versatile robot that can learn multiple tasks, but using RL for each of them would be prohibitively expensive in terms of both time and wear-and-tear on the robot. To remedy this problem, we use the Policy Gradient Efficient ...
متن کاملOnline Multi-Task Gradient Temporal-Difference Learning
Reinforcement learning (RL) is an essential tool in designing autonomous systems, yet RL agents often require extensive experience to achieve optimal behavior. This problem is compounded when an RL agent is required to learn policies for different tasks within the same environment or across multiple environments. In such situations, learning task models jointly rather than independently can sig...
متن کاملOnline Multi-Task Learning based on K-SVD
This paper develops an efficient online algorithm based on K-SVD for learning multiple consecutive tasks. We first derive a batch multi-task learning method that builds upon the K-SVD algorithm, and then extend the batch algorithm to train models online in a lifelong learning setting. The resulting method has lower computational complexity than other current lifelong learning algorithms while m...
متن کامل