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.

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2309.17207

Search this title in

Google Scholar