Efficient human-robot collaboration: when should a robot take initiative?

J Baraglia, M Cakmak, Y Nagai… - … Journal of Robotics …, 2017 - journals.sagepub.com
The promise of robots assisting humans in everyday tasks has led to a variety of research
questions and challenges in human-robot collaboration. Here, we address the question of …

Towards minimax optimal reinforcement learning in factored markov decision processes

Y Tian, J Qian, S Sra - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We study minimax optimal reinforcement learning in episodic factored Markov decision
processes (FMDPs), which are MDPs with conditionally independent transition components …

Maintenance optimisation of a parallel-series system with stochastic and economic dependence under limited maintenance capacity

Y Zhou, TR Lin, Y Sun, L Ma - Reliability Engineering & System Safety, 2016 - Elsevier
Maintenance optimisation of a parallel-series system considering both stochastic and
economic dependence among components as well as limited maintenance capacity is …

Situated dialogue learning through procedural environment generation

P Ammanabrolu, R Jia, MO Riedl - arxiv preprint arxiv:2110.03262, 2021 - arxiv.org
We teach goal-driven agents to interactively act and speak in situated environments by
training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019)--a …

Optimization of sequential decision making for chronic diseases: From data to decisions

BT Denton - Recent Advances in Optimization and Modeling …, 2018 - pubsonline.informs.org
Rapid advances in healthcare for chronic diseases such as cardiovascular disease, cancer,
and diabetes have made it possible to detect diseases at early stages and tailor treatment …

Recursive reinforcement learning

EM Hahn, M Perez, S Schewe… - Advances in …, 2022 - proceedings.neurips.cc
Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As
state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about …

Monte carlo tree search for trading and hedging

E Vittori, A Likmeta, M Restelli - … ACM International Conference on AI in …, 2021 - dl.acm.org
Monte Carlo Tree Search (MCTS) has had very exciting results in the field of two-player
games. In this paper, we analyze the behavior of these algorithms in the financial field, in …

An integrated approach to solving influence diagrams and finite-horizon partially observable decision processes

EA Hansen - Artificial Intelligence, 2021 - Elsevier
We show how to integrate a variable elimination approach to solving influence diagrams
with a value iteration approach to solving finite-horizon partially observable Markov decision …

Finding the best management policy to eradicate invasive species from spatial ecological networks with simultaneous actions

S Nicol, R Sabbadin, N Peyrard… - Journal of Applied …, 2017 - Wiley Online Library
Spatial management of invasive species is more likely to be successful when multiple
locations are treated simultaneously. However, selecting the best locations to act is difficult …

Reinforcement learning approaches in dynamic environments

M Han - 2018 - inria.hal.science
Reinforcement learning is learning from interaction with an environment to achieve a goal. It
is an efficient framework to solve sequential decision-making problems, using Markov …