Search Results for author: Raghuram Mandyam Annasamy

Found 3 papers, 2 papers with code

Towards Better Interpretability in Deep Q-Networks

1 code implementation15 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

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

no code implementations12 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.

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