MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning

Silva, Felipe Leno da; Glatt, Ruben; Costa, Anna Helena Reali

doi:10.1109/tcyb.2017.2781130

Cited by 30 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

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%

“…We have also explored the generalization capabilities provided by objectoriented representations [Silva et al 2019b]. Our first work leveraging this representation estimates Probabilistic Inter-TAsk Mappings (PITAM) [Silva and Costa 2017] through human-given task descriptions.…”

Section: Methods and Avenues For Future Workmentioning

confidence: 99%

“…This dissertation has also resulted in an object-oriented task description specialized for multiagent RL settings [Silva et al 2019b]. This description is easy to understand and to specify even to people without expertise in AI, and helps the learning agent to abstract knowledge (important for building TL approaches).…”

Section: Main Advances In the State Of The Artmentioning

confidence: 99%

See 2 more Smart Citations

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: Methods and Avenues For Future Workmentioning

confidence: 99%

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

show abstract

“…It too promotes learning of energy trading management where Agents arbitrate optimal solution from Agent's individualistic decision to gain uniform coalition payoff. Thus, probability stagnation schema was committed to ensure build-up convergence is attained during learning developments [26]- [28].…”

Section: Reinforced Learning For Cooperative Tendency In Layered Cmentioning

confidence: 99%

A Nano-Biased Energy Management Using Reinforced Learning Multi-Agent on Layered Coalition Model: Consumer Sovereignty

et al. 2019

View full text Add to dashboard Cite

Trends in energy management schema have advanced into legislating consumer-centered solutions due to inclination interests for personal owned distributed energy resources at the low-voltage level. Thence, this paper proposes a tailorable energy manager tool that empowers Prosumer(s) in a nanostructured distribution network to take sole precedence when prosuming optimal services to the energy system. It too acts as an aggregator that attests cooperative energy management processes amongst Prosumers to enhance demand-side responses and economics. The suggested nano-biased energy manager engages multi-agent network as the basis coordinator for peer-to-peer advocacy in a decentralized environment. The agents were then programmed with reinforcement and extreme learning machine intelligence on a layered coalition model to compute joint decision-making processes with constraint relaxation relaxed decision constraints and policies. The problem formulations assure engagement of energy management in the liberalized market is sustainable, reliable, and non-discriminated. Computational validations were analyzed using MATLAB and Java agent development framework on four aggregated Nanogrids representing the residential, commercial, and industrial building. Results have shown positive eco-strategic managerial avenues where cooperative assets scheduling and bidding-abled decorum were autonomously acquired. Reduced operating costs were gained from energy trading profit margin due to strategic use/sell of electricity based on real-time tariff and conferred incentive packages but constrained within the mandatory obligation to demand-side management. The subsidiary, the inauguration of meshed communication infrastructure has shown adequate monitoring and commanding resolutions for decentralized Agent(s) to function collaboratively. INDEX TERMS Demand-side management, multi-agent systems, adaptive scheduling, hybrid power system, stochastic processes and nanostructured power grid. NOMENCLATURE DER Distributed Renewable/Energy Resource DSO Distributed Network Operator ELM Extreme Learning Machine EM Energy Management JADE Java Agent DEvelopment LCM Layered Coalition Model MAN Multi-Agent Network MG Microgrid The associate editor coordinating the review of this manuscript and approving it for publication was Ramakrishnan Srinivasan.

show abstract

“…Reinforcement learning (RL) is an important machine learning method that has many applications in areas such as intelligent control of robots and analysis and prediction. The reinforcement learning algorithm can learn the mapping from environmental state to behavior, which makes the behavior selected by the agent can obtain the biggest reward of the environment [4,5]. However, reinforcement learning often faces dimensional disasters when the state of the system is large.…”

Section: Introductionmentioning

confidence: 99%

A Cognitive Relay Network Throughput Optimization Algorithm Based on Deep Reinforcement Learning

Liu

et al. 2019

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In cognitive relay networks, the cognitive user opportunistically accesses the authorized spectrum segment of the primary user and simultaneously serves as the data relay node of the primary user while sharing the spectrum resource of the primary user. This not only improves the utilization efficiency of the network spectrum resources but also improves the throughput of the primary users. However, if the primary user randomly selects the relay node, there is no guarantee for an optimal throughput. Moreover, the system power consumption may increase. In order to improve the throughput of cognitive relay network and optimize system utility, this paper proposes a cognitive relay network throughput optimization algorithm based on deep reinforcement learning. For the system model of cognitive relay networks, the Markov decision process is used to describe the channel transition probability of the system model in the paper. The algorithm proposes a cooperative wireless network cooperative relay strategy, analyzes the system outage probability under different transmission modes, and optimizes the system throughput by minimizing the outage probability. Then, the maximum utility optimization strategy based on deep reinforcement learning is proposed to maximize the system utility revenue by selecting the optimal behavior. The experimental results show that the proposed algorithm has a good effect in improving system throughput and optimizing system energy efficiency.

show abstract

MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning

Cited by 30 publications

References 20 publications

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

Methods and Algorithms for Knowledge Reuse in Multiagent Reinforcement Learning

A Nano-Biased Energy Management Using Reinforced Learning Multi-Agent on Layered Coalition Model: Consumer Sovereignty

A Cognitive Relay Network Throughput Optimization Algorithm Based on Deep Reinforcement Learning

Contact Info

Product

Resources

About