Integrating Neural Pathways for Learning in Deep Reinforcement Learning Models
Abstract
Considering that the human brain is the most powerful, generalizable, and energy-efficient computer we know of, it makes the most sense to look to neuroscience for ideas regarding deep learning model improvements. I propose one such idea, augmenting a traditional Advantage-Actor-Critic (A2C) model with additional learning signals akin to those in the brain. Pursuing this direction of research should hopefully result in a new reinforcement learning (RL) control paradigm that can learn from fewer examples, train with greater stability, and possibly consume less energy.
Cite
Text
Ananth. "Integrating Neural Pathways for Learning in Deep Reinforcement Learning Models." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30541Markdown
[Ananth. "Integrating Neural Pathways for Learning in Deep Reinforcement Learning Models." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/ananth2024aaai-integrating/) doi:10.1609/AAAI.V38I21.30541BibTeX
@inproceedings{ananth2024aaai-integrating,
title = {{Integrating Neural Pathways for Learning in Deep Reinforcement Learning Models}},
author = {Ananth, Varun},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2024},
pages = {23724-23725},
doi = {10.1609/AAAI.V38I21.30541},
url = {https://mlanthology.org/aaai/2024/ananth2024aaai-integrating/}
}