Online Adaptation of Deep Architectures with Reinforcement Learning

2016-08-08 · Thushan Ganegedara, Lionel Ott, Fabio Ramos

Online learning has become crucial to many problems in machine learning. As more data is collected sequentially, quickly adapting to changes in the data distribution can offer several competitive advantages such as avoiding loss of prior knowledge and more efficient learning. However, adaptation to changes in the data distribution (also known as covariate shift) needs to be performed without compromising past knowledge already built in into the model to cope with voluminous and dynamic data. In this paper, we propose an online stacked Denoising Autoencoder whose structure is adapted through reinforcement learning. Our algorithm forces the network to exploit and explore favourable architectures employing an estimated utility function that maximises the accuracy of an unseen validation sequence. Different actions, such as Pool, Increment and Merge are available to modify the structure of the network. As we observe through a series of experiments, our approach is more responsive, robust, and principled than its counterparts for non-stationary as well as stationary data distributions. Experimental results indicate that our algorithm performs better at preserving gained prior knowledge and responding to changes in the data distribution.

📄 PDF Abstract BibTeX arXiv:1608.02292

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems

2020-04-27 · Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen 외

Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments …

Meta Reinforcement Learning Minecraft reinforcement-learning Reinforcement Learning+1

Safe Continual Reinforcement Learning Methods for Nonstationary Environments. Towards a Survey of the State of the Art

2026-01-08 · Timofey Tomashevskiy arxiv

This work provides a state-of-the-art survey of continual safe online reinforcement learning (COSRL) methods. We discuss theoretical aspects, challenges, and open questions in building continual online safe reinforcement…

Reinforcement Learning Continual Learning

Solving Multi-Goal Robotic Tasks with Decision Transformer

2024-10-08 · Paul Gajewski, Dominik Żurek, Marcin Pietroń, Kamil Faber

Artificial intelligence plays a crucial role in robotics, with reinforcement learning (RL) emerging as one of the most promising approaches for robot control. However, several key challenges hinder its broader applicatio…

Multi-Goal Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MOORe: Model-based Offline-to-Online Reinforcement Learning

2022-01-25 · Yihuan Mao, Chao Wang, Bin Wang, Chongjie Zhang

With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online. A smooth transfer of the policy matters in safe real-world deployment. …

D4RL model reinforcement-learning Reinforcement Learning+1

Offline Meta Reinforcement Learning with In-Distribution Online Adaptation

2023-05-31 · Jianhao Wang, Jin Zhang, Haozhe Jiang, Junyu Zhang 외

Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a multi-task dataset. However, these methods a…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Uncertainty Quantification