Search Results for author: Mudita Sharma

Found 3 papers, 2 papers with code

Building a Legal Dialogue System: Development Process, Challenges and Opportunities

no code implementations1 Sep 2021 Mudita Sharma, Tony Russell-Rose, Lina Barakat, Akitaka Matsuo

This includes a training dataset, set of predetermined responses for the conversational agent, a set of regression test cases and a further conversation test set.

regression

Unified Framework for the Adaptive Operator Selection of Discrete Parameters

1 code implementation12 May 2020 Mudita Sharma, Manuel Lopez-Ibanez, Dimitar Kazakov

In addition to simplifying, we looked at the commonality among AOS methods from literature to generalise them.

Evolutionary Algorithms

Deep Reinforcement Learning Based Parameter Control in Differential Evolution

1 code implementation20 May 2019 Mudita Sharma, Alexandros Komninos, Manuel Lopez Ibanez, Dimitar Kazakov

Second, when DDQN is applied as a parameter controller within DE to a different test set of benchmark functions, DDQN uses the trained neural network to predict which mutation strategy should be applied to each parent at each generation according to the DE state.

Q-Learning reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.