107 citations · 146 across the 10 of their papers we have counts for
5 papers · 1 filter
Longer Attention Span: Increasing Transformer Context Length with Sparse Graph Processing Techniques
Nathaniel Tomczak, Sanmukh Kuppannagari
Transformers have demonstrated great success in numerous domains including natural language processing and bioinformatics. This success stems from the use of the attention mechanis…
A Framework to Enable Algorithmic Design Choice Exploration in DNNs
Timothy L. Cronin, Sanmukh Kuppannagari
Deep learning technologies, particularly deep neural networks (DNNs), have demonstrated significant success across many domains. This success has been accompanied by substantial ad…
BRAC+: Improved Behavior Regularized Actor Critic for Offline Reinforcement Learning
Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna
Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The go…
Parallel Actors and Learners: A Framework for Generating Scalable RL Implementations
Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna
Reinforcement Learning (RL) has achieved significant success in application domains such as robotics, games and health care. However, training RL agents is very time consuming. Cur…
Maximum Entropy Model Rollouts: Fast Model Based Policy Optimization without Compounding Errors
Chi Zhang, Sanmukh Rao Kuppannagari, Viktor K Prasanna
Model usage is the central challenge of model-based reinforcement learning. Although dynamics model based on deep neural networks provide good generalization for single step predic…