Saved in:
Bibliographic Details
Main Authors: Clinton, Joseph, Lieck, Robert
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.09513
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917775642984448
author Clinton, Joseph
Lieck, Robert
author_facet Clinton, Joseph
Lieck, Robert
contents Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with long-horizon tasks due to the high compounding error of auto-regressive models. To overcome this limitation, we go beyond next-token prediction and introduce Planning Tokens, which contain high-level, long time-scale information about the agent's future. Predicting dual time-scale tokens at regular intervals enables our model to use these long-horizon Planning Tokens as a form of implicit planning to guide its low-level policy and reduce compounding error. This architectural modification significantly enhances performance on long-horizon tasks, establishing a new state-of-the-art in complex D4RL environments. Additionally, we demonstrate that Planning Tokens improve the interpretability of the model's policy through the interpretable plan visualisations and attention map.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09513
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens
Clinton, Joseph
Lieck, Robert
Machine Learning
Artificial Intelligence
Computation and Language
Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with long-horizon tasks due to the high compounding error of auto-regressive models. To overcome this limitation, we go beyond next-token prediction and introduce Planning Tokens, which contain high-level, long time-scale information about the agent's future. Predicting dual time-scale tokens at regular intervals enables our model to use these long-horizon Planning Tokens as a form of implicit planning to guide its low-level policy and reduce compounding error. This architectural modification significantly enhances performance on long-horizon tasks, establishing a new state-of-the-art in complex D4RL environments. Additionally, we demonstrate that Planning Tokens improve the interpretability of the model's policy through the interpretable plan visualisations and attention map.
title Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2409.09513