paper-with-me

Papers

Multitask Soft Option Learning

2019-04-01 · Maximilian Igl, Andrew Gambardella, Jinke He, Nantas Nardelli, N. Siddharth, Wendelin Böhmer, Shimon Whiteson

We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This ''soft'' version of options avoids several instabilities during training in a multitask setting, and provides a natural way to learn both intra-option policies and their terminations. Furthermore, it allows fine-tuning of options for new tasks without forgetting their learned policies, leading to faster training without reducing the expressiveness of the hierarchical policy. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines.

📄 PDF Abstract BibTeX arXiv:1904.01033

Code (1)

maximilianigl/rl-msol 공식 구현 pytorch

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

Multitask Learning Deep Neural Networks to Combine Revealed and Stated Preference Data

2019-01-02 · Shenhao Wang, Qingyi Wang, Jinhua Zhao

It is an enduring question how to combine revealed preference (RP) and stated preference (SP) data to analyze travel behavior. This study presents a framework of multitask learning deep neural networks (MTLDNNs) for this…

Autonomous Vehicles

Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering

2017-10-31 · ICLR 2018 1 · Elliot Meyerson, Risto Miikkulainen

Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity o…

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model

2024-08-07 · Mingcan Xiang, Steven Jiaxun Tang, Qizheng Yang, Hui Guan 외

In the domain of multimedia and multimodal processing, the efficient handling of diverse data streams such as images, video, and sensor data is paramount. Model compression and multitask learning (MTL) are crucial in thi…

modelModel Compression

Evolutionary Architecture Search For Deep Multitask Networks

2018-03-10 · Jason Liang, Elliot Meyerson, Risto Miikkulainen

Multitask learning, i.e. learning several tasks at once with the same neural network, can improve performance in each of the tasks. Designing deep neural network architectures for multitask learning is a challenge: There…

Neural Architecture Search

How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging

2024-12-11 · Hugo Monzón Maldonado, Thomas Möllenhoff, Nico Daheim, Iryna Gurevych 외

When finetuning multiple tasks altogether, it is important to carefully weigh them to get a good performance, but searching for good weights can be difficult and costly. Here, we propose to aid the search with fast previ…