Agents teaching agents: a survey on inter-agent transfer learning

Silva, Felipe Leno da; Warnell, Garrett; Costa, Anna Helena Reali; Stone, Peter

doi:10.1007/s10458-019-09430-0

Cited by 64 publications

(43 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The following full papers are the main related publications: [Silva et al 2020a, Silva et al 2020b, Silva and Costa 2019, Silva et al 2019b, Silva et al 2020c, Silva et al 2019a, Silva et al 2016.…”

Section: Scientific Resultsmentioning

confidence: 99%

“…One of the contributions of this thesis was to write two surveys: one clearly organizing the literature on knowledge reuse in multiagent RL [Silva and Costa 2019], discussing the assumptions of each group of papers, and analyzing the difficulty in developing an integrated framework given the current state of the art. The second one [Silva et al 2020a] focused on the transfer of knowledge between agents, discussing all the current challenges in translating the knowledge from one agent to another.…”

Section: Main Advances In the State Of The Artmentioning

confidence: 99%

See 1 more Smart Citation

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

Silva¹,

Costa²

2020

Anais Do Concurso De Teses E Dissertações Da SBC (CTD-SBC 2020)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Scientific Resultsmentioning

confidence: 99%

Section: Main Advances In the State Of The Artmentioning

confidence: 99%

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

Silva¹,

Costa²

2020

Anais Do Concurso De Teses E Dissertações Da SBC (CTD-SBC 2020)

Self Cite

View full text Add to dashboard Cite

show abstract

“…• Breaking down learning phase with MAS: This future research highlights the problem of agent breeds learning to teach other agents within a MAS environment. The initial efforts have been via reinforcement learning [245] in which each agent takes the role of student or teacher, requesting and providing advice, respectively, at the appropriate moments looking forward an improved overall system performance [246]. There is a number of further challenges coming from this approach, to deal with complex domains for real-world applications.…”

Section: Multi-agent Systemsmentioning

confidence: 99%

A Review on Control and Optimisation of Multi-Agent Systems and Complex Networks for Systems Engineering

Herrera¹,

Hernández²,

Parlikad³

et al. 2020

Preprint

View full text Add to dashboard Cite

Systems Engineering is an ubiquitous discipline of Engineering overlapping industrial, chemical, mechanical, manufacturing, control, software, electrical, and civil engineering. It provides tools for dealing with the complexity and dynamics related to the optimisation of physical, natural, and virtual systems management. This paper presents a review of how multi-agent systems and complex networks theory are brought together to address Systems Engineering and management problems. The review also encompasses current and future research directions both for theoretical fundamentals and applications in Industry. This is made by considering trends such as mesoscale, multiscale, and multilayer networks; along with the state-of-art analysis on network dynamics and intelligent networks. Critical and smart infrastructure, manufacturing processes, and supply chain networks are instances of research topics for which this literature review is highly relevant.

show abstract

“…The knowledge obtained is not reused in the case of a negative transfer situation, such as a deadlock; however, it can be reused in other cases. In particular, in recent years, transfer in reinforcement learning in multi-agent systems and human robot teams has been discussed, and it is considered essential to avoid deadlock, that is, negative transfer by transfer learning [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Automatic Transfer Rate Adjustment for Transfer Reinforcement Learning

Kono¹,

Sakamoto²,

Ji³

et al. 2020

IJAIA

View full text Add to dashboard Cite

This paper proposes a novel parameter for transfer reinforcement learning to avoid over-fitting when an agent uses a transferred policy from a source task. Learning robot systems have recently been studied for many applications, such as home robots, communication robots, and warehouse robots. However, if the agent reuses the knowledge that has been sufficiently learned in the source task, deadlock may occur and appropriate transfer learning may not be realized. In the previous work, a parameter called transfer rate was proposed to adjust the ratio of transfer, and its contribution include avoiding dead lock in the target task. However, adjusting the parameter depends on human intuition and experiences. Furthermore, the method for deciding transfer rate has not discussed. Therefore, an automatic method for adjusting the transfer rate is proposed in this paper using a sigmoid function. Further, computer simulations are used to evaluate the effectiveness of the proposed method to improve the environmental adaptation performance in a target task, which refers to the situation of reusing knowledge.

show abstract

Agents teaching agents: a survey on inter-agent transfer learning

Cited by 64 publications

References 33 publications

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

A Review on Control and Optimisation of Multi-Agent Systems and Complex Networks for Systems Engineering

Automatic Transfer Rate Adjustment for Transfer Reinforcement Learning

Contact Info

Product

Resources

About