Deep reinforcement learning from self-play in imperfect-information games

J Heinrich, D Silver - arXiv preprint arXiv:1603.01121, 2016 - arxiv.org
Many real-world applications can be described as large-scale games of imperfect
information. To deal with these challenging domains, prior work has focused on computing …

Reinforcement learning for personalization: A systematic literature review

F Den Hengst, EM Grua, A el Hassouni… - Data …, 2020 - content.iospress.com
The major application areas of reinforcement learning (RL) have traditionally been game
playing and continuous control. In recent years, however, RL has been increasingly applied …

Competitive benchmarking

W Ketter, M Peters, J Collins, A Gupta - MIS quarterly, 2016 - JSTOR
Wicked problems like sustainable energy and financial market stability are societal
challenges that arise from complex sociotechnical systems in which numerous social …

A multiagent competitive gaming platform to address societal challenges

W Ketter, M Peters, J Collins, A Gupta - Mis Quarterly, 2016 - JSTOR
The shift toward sustainable electricity systems is one of the grand challenges of the 21st
century. Decentralized production from renewable sources, electric mobility, and related …

Summarizing agent strategies

O Amir, F Doshi-Velez, D Sarne - Autonomous Agents and Multi-Agent …, 2019 - Springer
Intelligent agents and AI-based systems are becoming increasingly prevalent. They support
people in different ways, such as providing users with advice, working with them to achieve …

Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer

R Traoré, H Caselles-Dupré, T Lesort, T Sun… - arXiv preprint arXiv …, 2019 - arxiv.org
We focus on the problem of teaching a robot to solve tasks presented sequentially, ie, in a
continual learning scenario. The robot should be able to solve all tasks it has encountered …

[PDF][PDF] Recurrent deep multiagent q-learning for autonomous brokers in smart grid.

Y Yang, J Hao, M Sun, Z Wang, C Fan, G Strbac - IJCAI, 2018 - nos.netease.com
The broker mechanism is widely applied to serve for interested parties to derive long-term
policies in order to reduce costs or gain profits in smart grid. However, a broker is faced with …

Efficiently detecting switches against non-stationary opponents

P Hernandez-Leal, Y Zhan, ME Taylor… - Autonomous Agents and …, 2017 - Springer
Interactions in multiagent systems are generally more complicated than single agent ones.
Game theory provides solutions on how to act in multiagent scenarios; however, it assumes …

[PDF][PDF] Agent strategy summarization

O Amir, F Doshi-Velez, D Sarne - Proceedings of the 17th …, 2018 - scholar.harvard.edu
Intelligent agents and AI-based systems are becoming increasingly prevalent. They support
people in different ways, such as providing users with advice, working with them to achieve …

Hierarchical decision making in electricity grid management

G Dalal, E Gilboa, S Mannor - International conference on …, 2016 - proceedings.mlr.press
The power grid is a complex and vital system that necessitates careful reliability
management. Managing the grid is a difficult problem with multiple time scales of decision …