scholarly journals A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems

2019 ◽  
Vol 64 ◽  
pp. 645-703 ◽  
Author(s):  
Felipe Leno Da Silva ◽  
Anna Helena Reali Costa
Keyword(s):  
Reinforcement Learning ◽  
Scale Up ◽  
Shared Environment ◽  
Complex Task ◽  
General Knowledge ◽  
Sample Complexity ◽  
Knowledge Reuse ◽  
Open Questions ◽  
Multiagent Reinforcement Learning ◽  
Current Lines

Multiagent Reinforcement Learning (RL) solves complex tasks that require coordination with other agents through autonomous exploration of the environment. However, learning a complex task from scratch is impractical due to the huge sample complexity of RL algorithms. For this reason, reusing knowledge that can come from previous experience or other agents is indispensable to scale up multiagent RL algorithms. This survey provides a unifying view of the literature on knowledge reuse in multiagent RL. We define a taxonomy of solutions for the general knowledge reuse problem, providing a comprehensive discussion of recent progress on knowledge reuse in Multiagent Systems (MAS) and of techniques for knowledge reuse across agents (that may be actuating in a shared environment or not). We aim at encouraging the community to work towards reusing all the knowledge sources available in a MAS. For that, we provide an in-depth discussion of current lines of research and open questions.

scholarly journals Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

2020 ◽  
Author(s):  
Felipe Leno Da Silva ◽  
Anna Helena Reali Costa
Keyword(s):  
Reinforcement Learning ◽  
Transfer Learning ◽  
Learning Process ◽  
Trial And Error ◽  
Knowledge Reuse ◽  
Previous Knowledge ◽  
Learning Methods ◽  
Types Of Knowledge ◽  
Learning Agent ◽  
Multiagent Reinforcement Learning

Reinforcement Learning (RL) is a powerful tool that has been used to solve increasingly complex tasks. RL operates through repeated interactions of the learning agent with the environment, via trial and error. However, this learning process is extremely slow, requiring many interactions. In this thesis, we leverage previous knowledge so as to accelerate learning in multiagent RL problems. We propose knowledge reuse both from previous tasks and from other agents. Several flexible methods are introduced so that each of these two types of knowledge reuse is possible. This thesis adds important steps towards more flexible and broadly applicable multiagent transfer learning methods.

scholarly journals Autonomously Reusing Knowledge in Multiagent Reinforcement Learning

2018 ◽  
Author(s):  
Felipe Leno Da Silva ◽  
Matthew E. Taylor ◽  
Anna Helena Reali Costa
Keyword(s):  
Reinforcement Learning ◽  
Autonomous Agents ◽  
Knowledge Reuse ◽  
Challenging Problem ◽  
Multiple Sources ◽  
Relevant Research ◽  
Core Technology ◽  
Multiagent Reinforcement Learning ◽  
Important Challenge ◽  
Research Challenge

Autonomous agents are increasingly required to solve complex tasks; hard-coding behaviors has become infeasible. Hence, agents must learn how to solve tasks via interactions with the environment. In many cases, knowledge reuse will be a core technology to keep training times reasonable, and for that, agents must be able to autonomously and consistently reuse knowledge from multiple sources, including both their own previous internal knowledge and from other agents. In this paper, we provide a literature review of methods for knowledge reuse in Multiagent Reinforcement Learning. We define an important challenge problem for the AI community, survey the existent methods, and discuss how they can all contribute to this challenging problem. Moreover, we highlight gaps in the current literature, motivating "low-hanging fruit'' for those interested in the area. Our ambition is that this paper will encourage the community to work on this difficult and relevant research challenge.

A Multi-Step Neural Control for Motor Brain-Machine Interface by Reinforcement Learning

2013 ◽  
Vol 461 ◽  
pp. 565-569 ◽  
Author(s):  
Fang Wang ◽  
Kai Xu ◽  
Qiao Sheng Zhang ◽  
Yi Wen Wang ◽  
Xiao Xiang Zheng
Keyword(s):  
Reinforcement Learning ◽  
Neural Activity ◽  
Neural Control ◽  
Brain Machine Interface ◽  
Learning Approach ◽  
Complex Task ◽  
Neural Data ◽  
Neural Spikes ◽  
Performance Improvements ◽  
Machine Interface

Brain-machine interfaces (BMIs) decode cortical neural spikes of paralyzed patients to control external devices for the purpose of movement restoration. Neuroplasticity induced by conducting a relatively complex task within multistep, is helpful to performance improvements of BMI system. Reinforcement learning (RL) allows the BMI system to interact with the environment to learn the task adaptively without a teacher signal, which is more appropriate to the case for paralyzed patients. In this work, we proposed to apply Q(λ)-learning to multistep goal-directed tasks using users neural activity. Neural data were recorded from M1 of a monkey manipulating a joystick in a center-out task. Compared with a supervised learning approach, significant BMI control was achieved with correct directional decoding in 84.2% and 81% of the trials from naïve states. The results demonstrate that the BMI system was able to complete a task by interacting with the environment, indicating that RL-based methods have the potential to develop more natural BMI systems.

OBSTACLES TO INNOVATION FOR SMEs: EVIDENCE FROM GERMANY

2017 ◽  
Vol 21 (03) ◽  
pp. 1750030 ◽  
Author(s):  
NATALIA STROBEL ◽  
JAN KRATZER
Keyword(s):  
Theoretical Framework ◽  
Complex Task ◽  
Competitive Performance ◽  
Structured Interviews ◽  
Innovative Performance ◽  
Face To Face ◽  
Know How ◽  
Open Questions

Achieving effective innovation is a complex task and during this process, firms [especially small and medium sized enterprises (SMEs)] often face obstacles. However, research into obstacles to innovation focusing on SMEs is very scarce. In this study, we propose a theoretical framework for describing these obstacles to innovation and investigate their influence on the innovative performance of SMEs. Data were collected in 2013 through face-to-face interviews with executives of 49 technology SMEs from Germany. The semi-structured interviews were designed on the basis of scales for measuring innovativeness, financial/competitive performance and obstacles to innovation, next to purely open questions. We find that the internal obstacles, lack of know-how, capacity overloading, unclear roles and tasks as well as the external obstacle governmental bureaucracy negatively influence innovative performance of SMEs. However, in contrast to prior findings, this study shows that cooperation ties of firms might also negatively influence the innovative performance.

Sign in / Sign up

Export Citation Format

Share Document