Combining Model-Free Q-Ensembles and Model-Based Approaches for Informed Exploration

no code implementations • 12 Jun 2018 • Sreecharan Sankaranarayanan, Raghuram Mandyam Annasamy, Katia Sycara, Carolyn Penstein Rosé

Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained.

Towards Better Interpretability in Deep Q-Networks

1 code implementation • 15 Sep 2018 • Raghuram Mandyam Annasamy, Katia Sycara

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments.

Q-Learning Reinforcement Learning (RL)

Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification

1 code implementation • WS 2019 • Vaibhav Vaibhav, Raghuram Mandyam Annasamy, Eduard Hovy

The rising growth of fake news and misleading information through online media outlets demands an automatic method for detecting such news articles.

Feature Engineering General Classification +2