Steven D. Morad

Steven D. Morad

Reinforcement learning @Cambridge

Reinforcement Learning with Fast and Forgetful Memory

Published in Thirty-seventh Conference on Neural Information Processing Systems, 2023

Arxiv, OpenReview

A new memory model, tuned specifically for RL

@inproceedings{
morad2023popgym,
title={POPGym: Benchmarking Partially Observable Reinforcement Learning},
author={Steven Morad and Ryan Kortvelesy and Matteo Bettini and Stephan Liwicki and Amanda Prorok},
booktitle={The Eleventh International Conference on Learning Representations},
year={2023},
url={https://openreview.net/forum?id=chDrutUTs0K}
}