• Publications
  • Influence
Lexicase selection in learning classifier systems
TLDR
It is shown that batch-lexicase selection results in the creation of more generic rules which are favorable for generalization on future data, and results in better generalization in situations of partial or missing data. Expand
Reinforcement learning with a network of spiking agents
TLDR
It is shown that a network of GLM spiking agents connected in a hierarchical fashion, where each spiking agent modulates its firing policy based on local information and a global prediction error, can learn complex action representations to solve reinforcement learning (RL) tasks. Expand
Training spiking neural networks using reinforcement learning
TLDR
This project proposes biologically-plausible alternatives to backpropagation to facilitate the training of spiking neural networks and investigates the candidacy of reinforcement learning (RL) rules in solving the spatial and temporal credit assignment problems to enable decision-making in complex tasks. Expand
Reinforcement learning with spiking coagents
TLDR
It is shown that a network of GLM spiking agents connected in a hierarchical fashion, where each spiking agent modulates its firing policy based on local information and a global prediction error, can learn complex action representations to solve reinforcement learning (RL) tasks. Expand
A memory enhanced LSTM for modeling complex temporal dependencies
  • Sneha Aenugu
  • Computer Science, Mathematics
  • ArXiv
  • 25 October 2019
In this paper, we present Gamma-LSTM, an enhanced long short term memory (LSTM) unit, to enable learning of hierarchical representations through multiple stages of temporal abstractions. GammaExpand
Perturbation-based exploration methods in deep reinforcement learning
TLDR
It is shown that simple acts of perturbing the policy just before the softmax layer and introduction of sporadic reward bonuses into the domain can greatly enhance exploration in several domains of the arcade learning environment. Expand