Efficient human-robot collaboration: when should a robot take initiative?
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 …
questions and challenges in human-robot collaboration. Here, we address the question of …
Towards minimax optimal reinforcement learning in factored markov decision processes
We study minimax optimal reinforcement learning in episodic factored Markov decision
processes (FMDPs), which are MDPs with conditionally independent transition components …
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 …
economic dependence among components as well as limited maintenance capacity is …
Situated dialogue learning through procedural environment generation
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 …
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 …
and diabetes have made it possible to detect diseases at early stages and tailor treatment …
Recursive reinforcement learning
Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As
state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about …
state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about …
Monte carlo tree search for trading and hedging
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 …
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 …
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
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 …
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 …
is an efficient framework to solve sequential decision-making problems, using Markov …