Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
M. Pleines, M. Pallasch, F. Zimmer, M. Preuss, ArXiv:2309.17207 (2023).
Download
No fulltext has been uploaded.
Preprint
| English
Author
Pleines, Marco;
Pallasch, Matthias;
Zimmer, Frank;
Preuss, Mike
Abstract
Memory Gym presents a suite of 2D partially observable environments, namely
Mortar Mayhem, Mystery Path, and Searing Spotlights, designed to benchmark
memory capabilities in decision-making agents. These environments, originally
with finite tasks, are expanded into innovative, endless formats, mirroring the
escalating challenges of cumulative memory games such as ``I packed my bag''.
This progression in task design shifts the focus from merely assessing sample
efficiency to also probing the levels of memory effectiveness in dynamic,
prolonged scenarios. To address the gap in available memory-based Deep
Reinforcement Learning baselines, we introduce an implementation that
integrates Transformer-XL (TrXL) with Proximal Policy Optimization. This
approach utilizes TrXL as a form of episodic memory, employing a sliding window
technique. Our comparative study between the Gated Recurrent Unit (GRU) and
TrXL reveals varied performances across different settings. TrXL, on the finite
environments, demonstrates superior sample efficiency in Mystery Path and
outperforms in Mortar Mayhem. However, GRU is more efficient on Searing
Spotlights. Most notably, in all endless tasks, GRU makes a remarkable
resurgence, consistently outperforming TrXL by significant margins. Website and
Source Code: https://github.com/MarcoMeter/endless-memory-gym/
Publishing Year
Journal Title
arXiv:2309.17207
LibreCat-ID
Cite this
Pleines M, Pallasch M, Zimmer F, Preuss M. Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents. arXiv:230917207. Published online 2023.
Pleines, M., Pallasch, M., Zimmer, F., & Preuss, M. (2023). Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents. In arXiv:2309.17207.
@article{Pleines_Pallasch_Zimmer_Preuss_2023, title={Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents}, journal={arXiv:2309.17207}, author={Pleines, Marco and Pallasch, Matthias and Zimmer, Frank and Preuss, Mike}, year={2023} }
Pleines, Marco, Matthias Pallasch, Frank Zimmer, and Mike Preuss. “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents.” ArXiv:2309.17207, 2023.
M. Pleines, M. Pallasch, F. Zimmer, and M. Preuss, “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents,” arXiv:2309.17207. 2023.
Pleines, Marco, et al. “Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents.” ArXiv:2309.17207, 2023.