A survey on intrinsic motivation in reinforcement learning

A Aubret, L Matignon, S Hassas - arxiv preprint arxiv:1908.06976, 2019 - arxiv.org
The reinforcement learning (RL) research area is very active, with an important number of
new contributions; especially considering the emergent field of deep RL (DRL). However a …

Trajectory diversity for zero-shot coordination

A Lupu, B Cui, H Hu, J Foerster - … conference on machine …, 2021 - proceedings.mlr.press
We study the problem of zero-shot coordination (ZSC), where agents must independently
produce strategies for a collaborative game that are compatible with novel partners not seen …

Too many cooks: Bayesian inference for coordinating multi‐agent collaboration

SA Wu, RE Wang, JA Evans… - Topics in Cognitive …, 2021 - Wiley Online Library
Collaboration requires agents to coordinate their behavior on the fly, sometimes cooperating
to solve a single task together and other times dividing it up into sub‐tasks to work on in …

Deep learning applications in games: a survey from a data perspective

Z Hu, Y Ding, R Wu, L Li, R Zhang, Y Hu, F Qiu… - Applied …, 2023 - Springer
This paper presents a comprehensive review of deep learning applications in the video
game industry, focusing on how these techniques can be utilized in game development …

Hierarchical reinforcement learning with adaptive scheduling for robot control

Z Huang, Q Liu, F Zhu - Engineering Applications of Artificial Intelligence, 2023 - Elsevier
Conventional hierarchical reinforcement learning (HRL) relies on discrete options to
represent explicitly distinguishable knowledge, which may lead to severe performance …

Towards efficient long-horizon decision-making using automated structure search method of hierarchical reinforcement learning for edge artificial intelligence

G Wu, W Bao, J Cao, X Zhu, J Wang, W **ao, W Liang - Internet of Things, 2023 - Elsevier
Hierarchical reinforcement learning (HRL) is a promising approach for efficiently solving
various long-horizon decision-making tasks in the Internet of Things (IoT) domain. However …

A study of deep reinforcement learning based recommender systems

G Gupta, R Katarya - 2021 2nd International conference on …, 2021 - ieeexplore.ieee.org
With the advancement in new technologies and a massive amount of data every day,
various tools and models are being introduced to tackle such data. Such a branch of …

VNE-HRL: A proactive virtual network embedding algorithm based on hierarchical reinforcement learning

J Cheng, Y Wu, Y Lin, E Yuepeng… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Virtual network embedding (VNE) that instantiates virtualized networks on a substrate
infrastructure, is one of the key research problems for network virtualization. Most existing …

Beyond rewards: a hierarchical perspective on offline multiagent behavioral analysis

S Omidshafiei, A Kapishnikov… - Advances in …, 2022 - proceedings.neurips.cc
Each year, expert-level performance is attained in increasingly-complex multiagent
domains, where notable examples include Go, Poker, and StarCraft II. This rapid …

Resonating minds—emergent collaboration through hierarchical active inference

J Pöppel, S Kahl, S Kopp - Cognitive Computation, 2022 - Springer
Working together on complex collaborative tasks requires agents to coordinate their actions.
Doing this explicitly or completely prior to the actual interaction is not always possible nor …