scholarly journals Inter-Task Similarity for Lifelong Reinforcement Learning in Heterogeneous Tasks

2021 ◽  
Author(s):  
Sergio A. Serrano
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Lifelong Learning ◽  
Learning Approach ◽  
Trial And Error ◽  
Learning Paradigm ◽  
Service Robotics ◽  
State Action ◽  
Task Similarity ◽  
High Degree

Reinforcement learning (RL) is a learning paradigm in which an agent interacts with the environment it inhabits to learn in a trial-and-error way. By letting the agent acquire knowledge from its own experience, RL has been successfully applied to complex domains such as robotics. However, for non-trivial problems, training an RL agent can take very long periods of time. Lifelong machine learning (LML) is a learning setting in which the agent learns to solve tasks sequentially, by leveraging knowledge accumulated from previously solved tasks to learn better/faster in a new one. Most LML works heavily rely on the assumption that tasks are similar to each other. However, this may not be true for some domains with a high degree of task-diversity that could benefit from adopting a lifelong learning approach, e.g., service robotics. Therefore, in this research we will address the problem of learning to solve a sequence of RL heterogeneous tasks (i.e., tasks that differ in their state-action space).

scholarly journals Efficient Training Management for Mobile Crowd-Machine Learning: A Deep Reinforcement Learning Approach

2019 ◽  
Vol 8 (5) ◽  
pp. 1345-1348 ◽  
Author(s):  
Tran The Anh ◽  
Nguyen Cong Luong ◽  
Dusit Niyato ◽  
Dong In Kim ◽  
Li-Chun Wang
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Learning Approach ◽  
Mobile Crowd

Reinforcement Learning's Contribution to the Cyber Security of Distributed Systems

2020 ◽  
Vol 12 (2) ◽  
pp. 35-55
Author(s):  
Christophe Feltus
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Systematic Review ◽  
Information System ◽  
Reinforcement Learning ◽  
Distributed Systems ◽  
Unsupervised Learning ◽  
Cyber Security ◽  
Analytic Framework ◽  
Learning Paradigm

Reinforcement learning (RL) is a machine learning paradigm, like supervised or unsupervised learning, which learns the best actions an agent needs to perform to maximize its rewards in a particular environment. Research into RL has been proven to have made a real contribution to the protection of cyberphysical distributed systems. In this paper, the authors propose an analytic framework constituted of five security fields and eight industrial areas. This framework allows structuring a systematic review of the research in artificial intelligence that contributes to cybersecurity. In this contribution, the framework is used to analyse the trends and future fields of interest for the RL-based research in information system security.

Design of Transfer Reinforcement Learning Under Low Task Similarity

2018 ◽  
Author(s):  
Xiongqing Liu ◽  
Yan Jin
Keyword(s):  
Reinforcement Learning ◽  
Case Studies ◽  
Collision Avoidance ◽  
Negative Transfer ◽  
Learning Approach ◽  
Complex Task ◽  
Simple Task ◽  
Task Similarity

In this paper, a deep reinforcement learning approach was implemented to achieve autonomous collision avoidance. A transfer reinforcement learning approach (TRL) was proposed by introducing two concepts: transfer belief — how much confidence the agent puts in the expert’s experience, and transfer period — how long the agent’s decision is influenced by the expert’s experience. Various case studies have been conducted on transfer from a simple task — single static obstacle, to a complex task — multiple dynamic obstacles. It is found that if two tasks have low similarity, it is better to decrease initial transfer belief and keep a relatively longer transfer period, in order to reduce negative transfer and boost learning. Student agent’s learning variance grows significantly if using too short transfer period.

scholarly journals Deep Reinforcement Learning of Transition States

2021 ◽  
Author(s):  
Jun Zhang ◽  
Yao-Kun Lei ◽  
Zhen Zhang ◽  
Xu Han ◽  
Maodong Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Dynamics ◽  
Reinforcement Learning ◽  
Transition State ◽  
Chemical Reaction ◽  
Reaction Mechanisms ◽  
Md Simulations ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Chemical Reaction Mechanisms

Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach, called RL‡, to automatically unravel chemical reaction mechanisms. In RL‡, locating the transition state of a...

scholarly journals Effective Use of Learning Knowledge by FEERL

2003 ◽  
Vol 7 (1) ◽  
pp. 6-9
Author(s):  
Yukinobu Hoshino ◽  
◽  
Katsuari Kamei
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Learning System ◽  
Trial And Error ◽  
Fuzzy Environment ◽  
Learning Techniques ◽  
Training Examples ◽  
Effective Use

The machine learning is proposed to learning techniques of spcialists. A machine has to learn techniques by trial and error when there are no training examples. Reinforcement learning is a powerful machine learning system, which is able to learn without giving training examples to a learning unit. But it is impossible for the reinforcement learning to support large environments because the number of if-then rules is a huge combination of a relationship between one environment and one action. We have proposed new reinforcement learning system for the large environment, Fuzzy Environment Evaluation Reinforcement Learning (FEERL). In this paper, we proposed to reuse of the acquired rules by FEERL.

scholarly journals Lifelong Machine Learning Architecture for Classification

Symmetry ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 852
Author(s):  
Xianbin Hong ◽  
Sheng-Uei Guan ◽  
Ka Lok Man ◽  
Prudence W. H. Wong
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Lifelong Learning ◽  
High Performance ◽  
Rapid Development ◽  
Learning Approach ◽  
Continuous Learning ◽  
Improve Performance ◽  
Data Volume ◽  
Performance Computing

Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is isolated with others. Although open source datasets are available, algorithms’ performance is asymmetric with the data volume. Hence, the AI community wishes to raise a symmetric continuous learning architecture which can automatically learn and adapt to different tasks. Such a learning architecture also is commonly called as lifelong machine learning (LML). This learning paradigm could manage the learning process and accumulate meta-knowledge by itself during learning different tasks. The meta-knowledge is shared among all tasks symmetrically to help them to improve performance. With the growth of meta-knowledge, the performance of each task is expected to be better and better. In order to demonstrate the application of lifelong machine learning, this paper proposed a novel and symmetric lifelong learning approach for sentiment classification as an example to show how it adapts different domains and keeps efficiency meanwhile.

Sign in / Sign up

Export Citation Format

Share Document