Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state ...

We assume that service robots will have spare time in between scheduled user requests, which they could use to perform additional unrequested services in order to learn a model of users' preferences and receive reward. However, a mobile service robot is ...

The broker mechanism is widely applied to serve for interested parties to derive long-term policies to reduce costs or gain profits in smart grid. However, brokers are faced with a number of challenging problems such as balancing demand and supply from ...

This paper studies a variation of stochastic multi-armed bandit (MAB) problem where the agent knows a prior knowledge named Near-optimal Mean Reward (NoMR). We show that the cumulative regret of this bandit variation has a lower bound of Ω Δeft(1/Δ), ...

During training, model-free reinforcement learning (RL) systems can explore actions that lead to harmful or costly consequences. Having a human "in the loop'' and ready to intervene at all times can prevent these mistakes, but is prohibitively expensive ...

Imitation learning algorithms learn viable policies by imitating an expert's behavior when reward signals are not available. Generative Adversarial Imitation Learning (GAIL) is a state-of-the-art algorithm for learning policies when the expert's ...

Due to the limited generation capacity of power stations, many developing countries frequently resort to disconnecting large parts of the power grid from supply, a process termed load shedding. This leaves homes without electricity, causing them ...

In the micro-tolling paradigm, different toll values are assigned to different links within a congestible traffic network. Self-interested agents then select minimal cost routes, where cost is a function of the travel time and tolls paid. A centralized ...

Learning from a target has been tackled in the reinforcement learning (RL) setting [1, 7] as imitation learning, either through behaviour cloning or inverse RL. In the former, the agent regresses directly onto the policy of a target [5], while in the ...

Reinforcement learning is a paradigm to model how an autonomous agent learns to maximise its cumulative reward by interacting with the environment. One challenge faced by reinforcement learning is that in many environments the reward signal is sparse, ...

In this work we present a technique for using natural language to help reinforcement learning generalize to unseen environments using neural machine translation techniques. These techniques are then integrated into policy shaping to make it more ...

In urban areas across the globe, incidents like crime, fire and accidents often result in massive losses of life and property. In such scenarios, quick response can minimize or prevent damage. Emergency responder services are eager to adopt mechanisms ...

Ongoing digitization of all kinds of human enterprise is allowing sophisticated pricing strategies to be used in domains where previously this has not been feasible. In the mobility domain, commodities such as shared cars or electric vehicle charging ...

The objective of this research is to provide scalable decision making algorithms for autonomously navigating urban environments. The vehicle must plan in a stochastic environment with many entities to avoid, rapid changes in driver behavior, and partial ...

Existence can perhaps be viewed an exercise of searching high-dimensional, rugged, and approximated (using training data) landscapes for (often time-delayed) rewards. Bounded rationality imposes limits on the success of solutions that can be found by ...

Computational epidemiologists frequently employ large-scale agent-based simulations of human populations to study disease outbreaks and assess intervention strategies. The agents used in such simulations rarely capture the real-world decision-making of ...

Humans are able to understand and perform complex tasks by strategically structuring tasks into incremental steps or sub-goals. For a robot attempting to learn to perform a sequential task with critical subgoal states, these subgoal states can provide a ...

Crowdsourcing systems have become a valuable solution for various organizations to outsource work on a temporary basis. Quality assurance in these systems remains a key issue due to the distributed setup of the crowdsourcing platforms and the absence of ...

The reinforcement learning literature typically assumes fixed state transition functions for the sake of tractability. However, in many real-world tasks, the state transition function changes over time, and this change may be governed by exogenous ...