Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2024 International Joint Conference on Neural Networks (IJCNN), 2024, 00, pp. 1-8
- Issue Date:
- 2024-09-09
Embargoed
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Decoupling Exploration and Exploitation for Unsupervised Pre-training with Successor Features.pdf | Accepted version | 530.46 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is currently unavailable due to the publisher's embargo.
Unsupervised pre training has been on the lookout for the virtue of a value function representation referred to as successor features SFs which decouples the dynamics of the environment from the rewards It has a significant impact on the process of task specific fine tuning due to the decomposition However existing approaches struggle with local optima due to the unified intrinsic reward of exploration and exploitation without considering the linear regression problem and the discriminator supporting a small skill sapce We propose a novel unsupervised pre training model with SFs based on a non monolithic exploration methodology Our approach pursues the decomposition of exploitation and exploration of an agent built on SFs which requires separate agents for the respective purpose The idea will leverage not only the inherent characteristics of SFs such as a quick adaptation to new tasks but also the exploratory and task agnostic capabilities Our suggested model is termed Non Monolithic unsupervised Pretraining with Successor features NMPS which improves the performance of the original monolithic exploration method of pre training with SFs NMPS outperforms Active Pre training with Successor Features APS in a comparative experiment
Please use this identifier to cite or link to this item: