Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces
Continual offline reinforcement learning (CORL) has shown impressive ability in diffusion-based lifelong learning systems by modeling the joint distributions of trajectories. However, most research only focuses on limited continual task settings where the tasks have the same observation and action s...
Gespeichert in:
Hauptverfasser: | , , , , , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Continual offline reinforcement learning (CORL) has shown impressive ability
in diffusion-based lifelong learning systems by modeling the joint
distributions of trajectories. However, most research only focuses on limited
continual task settings where the tasks have the same observation and action
space, which deviates from the realistic demands of training agents in various
environments. In view of this, we propose Vector-Quantized Continual Diffuser,
named VQ-CD, to break the barrier of different spaces between various tasks.
Specifically, our method contains two complementary sections, where the
quantization spaces alignment provides a unified basis for the selective
weights activation. In the quantized spaces alignment, we leverage vector
quantization to align the different state and action spaces of various tasks,
facilitating continual training in the same space. Then, we propose to leverage
a unified diffusion model attached by the inverse dynamic model to master all
tasks by selectively activating different weights according to the task-related
sparse masks. Finally, we conduct extensive experiments on 15 continual
learning (CL) tasks, including conventional CL task settings (identical state
and action spaces) and general CL task settings (various state and action
spaces). Compared with 16 baselines, our method reaches the SOTA performance. |
---|---|
DOI: | 10.48550/arxiv.2410.15698 |