Multi-disciplinary Trends in Artificial Intelligence
8th International Workshop, MIWAI 2014, Bangalore, India, December 8-10, 2014. Proceedings
Article
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or...
Article
Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. ...
Chapter and Conference Paper
Learning fair policies in reinforcement learning (RL) is important when the RL agent’s actions may impact many users. In this paper, we investigate a generalization of this problem where equity is still desire...
Chapter and Conference Paper
Branch-and-Cut is a widely-used method for solving integer programming problems exactly. In recent years, researchers have been exploring ways to use Machine Learning to improve the decision-making process of ...
Chapter and Conference Paper
To improve the sample efficiency of vision-based deep reinforcement learning (RL), we propose a novel method, called SPIRL, to automatically extract important patches from input images. Following Masked Auto-Enco...
Chapter and Conference Paper
Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in...
Chapter and Conference Paper
Learning a policy from sparse rewards is a main challenge in reinforcement learning (RL). The best solutions to this challenge have been via sample inefficient model-free RL algorithms. Model-based RL algorith...
Chapter
Reinforcement learning (RL) is a general framework for adaptive control, which has proven to be efficient in many domains, e.g., board games, video games or autonomous vehicles. In such problems, an agent face...
Chapter
A microgrid is an integrated energy system consisting of distributed energy resources and multiple electrical loads operating as a single, autonomous grid either in parallel to or “islanded” from the existing ...
Article
With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many s...
Chapter and Conference Paper
With the simultaneous rise of energy costs and demand for cloud computing, efficient control of data centers becomes crucial. In the data center control problem, one needs to plan at every time step how many s...
Chapter and Conference Paper
We consider a general class of combinatorial optimization problems including among others allocation, multiple knapsack, matching or travelling salesman problems. The standard version of those problems is the ...
Chapter and Conference Paper
In this paper, we present a link between preference-based and multiobjective sequential decision-making. While transforming a multiobjective problem to a preference-based one is quite natural, the other direct...
Chapter and Conference Paper
In this paper, we tackle the problem of risk-averse route planning in a transportation network with time-dependent and stochastic costs. To solve this problem, we propose an adaptation of the A* algorithm that...
Chapter and Conference Paper
To tackle the potentially hard task of defining the reward function in a Markov Decision Process (MDPs), a new approach, called Interactive Value Iteration (IVI) has recently been proposed by Weng and Zanuttin...
Article
We introduce a novel approach to preference-based reinforcement learning, namely a preference-based variant of a direct policy search method based on evolutionary optimization. The core of our approach is a pr...
Book and Conference Proceedings
8th International Workshop, MIWAI 2014, Bangalore, India, December 8-10, 2014. Proceedings
Chapter and Conference Paper
Hidden-Mode Markov Decision Processes (HM-MDPs) were proposed to represent sequential decision-making problems in non-stationary environments that evolve according to a Markov chain. We introduce in this paper...
Chapter and Conference Paper
The aim of this paper is to provide a unifying axiomatic justification for a class of qualitative decision models comprising among others optimistic/pessimistic qualitative utilities, binary possibilistic util...
Chapter and Conference Paper
Markov decision processes (MDP) have become one of the standard models for decision-theoretic planning problems under uncertainty. In its standard form, rewards are assumed to be numerical additive scalars. In...