Saved in:
Bibliographic Details
Main Authors: Yue, William, Liu, Bo, Stone, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.07954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917835871092736
author Yue, William
Liu, Bo
Stone, Peter
author_facet Yue, William
Liu, Bo
Stone, Peter
contents In Partially Observable Markov Decision Processes, integrating an agent's history into memory poses a significant challenge for decision-making. Traditional imitation learning, relying on observation-action pairs for expert demonstrations, fails to capture the expert's memory mechanisms used in decision-making. To capture memory processes as demonstrations, we introduce the concept of memory dependency pairs $(p, q)$ indicating that events at time $p$ are recalled for decision-making at time $q$. We introduce AttentionTuner to leverage memory dependency pairs in Transformers and find significant improvements across several tasks compared to standard Transformers when evaluated on Memory Gym and the Long-term Memory Benchmark. Code is available at https://github.com/WilliamYue37/AttentionTuner.
format Preprint
id arxiv_https___arxiv_org_abs_2411_07954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Memory Mechanisms for Decision Making through Demonstrations
Yue, William
Liu, Bo
Stone, Peter
Machine Learning
Robotics
In Partially Observable Markov Decision Processes, integrating an agent's history into memory poses a significant challenge for decision-making. Traditional imitation learning, relying on observation-action pairs for expert demonstrations, fails to capture the expert's memory mechanisms used in decision-making. To capture memory processes as demonstrations, we introduce the concept of memory dependency pairs $(p, q)$ indicating that events at time $p$ are recalled for decision-making at time $q$. We introduce AttentionTuner to leverage memory dependency pairs in Transformers and find significant improvements across several tasks compared to standard Transformers when evaluated on Memory Gym and the Long-term Memory Benchmark. Code is available at https://github.com/WilliamYue37/AttentionTuner.
title Learning Memory Mechanisms for Decision Making through Demonstrations
topic Machine Learning
Robotics
url https://arxiv.org/abs/2411.07954