Saved in:
Bibliographic Details
Main Authors: Kumawat, Hemant, Mukhopadhyay, Saibal
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.15427
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909435802157056
author Kumawat, Hemant
Mukhopadhyay, Saibal
author_facet Kumawat, Hemant
Mukhopadhyay, Saibal
contents Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the environment in offline RL settings. However, these models tend to over-rely on memorizing long-term representations, which impairs their ability to effectively attribute importance to trajectories and learned representations based on task-specific relevance. In this work, we introduce AdaCred, a novel approach that represents trajectories as causal graphs built from short-term action-reward-state sequences. Our model adaptively learns control policy by crediting and pruning low-importance representations, retaining only those most relevant for the downstream task. Our experiments demonstrate that AdaCred-based policies require shorter trajectory sequences and consistently outperform conventional methods in both offline reinforcement learning and imitation learning environments.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15427
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AdaCred: Adaptive Causal Decision Transformers with Feature Crediting
Kumawat, Hemant
Mukhopadhyay, Saibal
Machine Learning
Robotics
Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the environment in offline RL settings. However, these models tend to over-rely on memorizing long-term representations, which impairs their ability to effectively attribute importance to trajectories and learned representations based on task-specific relevance. In this work, we introduce AdaCred, a novel approach that represents trajectories as causal graphs built from short-term action-reward-state sequences. Our model adaptively learns control policy by crediting and pruning low-importance representations, retaining only those most relevant for the downstream task. Our experiments demonstrate that AdaCred-based policies require shorter trajectory sequences and consistently outperform conventional methods in both offline reinforcement learning and imitation learning environments.
title AdaCred: Adaptive Causal Decision Transformers with Feature Crediting
topic Machine Learning
Robotics
url https://arxiv.org/abs/2412.15427