Links [1] https://www.uoguelph.ca/hr/policies/back-care-policy [2] https://www.uoguelph.ca/hr/policies/bloodborne-pathogens-policy [3] https://www.uoguelph.ca/hr/policies/confidentiality-employee-health-and-medical-records-policy [4] https://www.uoguelph.ca/hr/policies/consumption-alcoholic-beverages-university-property-policy [5] https://www.uoguelph.ca/hr/policies/employee-assistance-program-...

This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both standard RL and inverse reinforcement learning. Although with a limited expertise, the human expert is still often able to emit preferences and rank the agent de...

We propose an algorithm for estimating the finite-horizon expected return of a closed loop control policy from an a priori given (off-policy) sample of one-step transitions. It averages cumulated rewards along a set of “broken trajectories” made of one-step transitions selected from the sample on the basis of the control policy. Under some Lipschitz continuity assumptions on the system dynamics...

A policy gradient method is a reinforcement learning approach that directly optimizes a parametrized control policy by gradient descent. It belongs to the class of policy search techniques that maximize the expected return of a policy in a fixed policy class while traditional value function approximation approaches derive policies from a value function. Policy gradient approaches have various a...

In this article, we model money-back guarantees (MBGs) as put options. This use of option theory provides retailers with a framework to optimize the price and the return option independently and under various market conditions. This separation of product price and option value enables retailers to offer an unbundled MBG policy, that is, to allow the customer to choose whether to purchase an MBG...

An agricultural water conservation policy prevalent worldwide encourages producers to improve on-farm irrigation efficiency. Contrary to intention, increasing empirical evidence reveals that this policy may set an ‘irrigation efficiency trap’ that worsens water crises by reducing water supplies and jeopardizing economic growth. We derive a pair of testable hydrologic-economic conditions require...

This study investigates the impact of 306 strategic alliances on the increment of firm value in the case of China. I apply the event study methodology using OLS market model to examine the abnormal returns of sample firms. The results show that the announcements of strategic alliance in China generate significant positive average abnormal return on the announcement date (0.96%) which reaches 1%...

—This work addresses the problem of how a robot can improve a manipulation skill in a sample-efficient and secure manner. As an alternative to the standard reinforcement learning formulation where all objectives are defined in a single reward function, we propose a generalized formulation that consists of three components: 1) A known analytic control cost function; 2) A black-box return functio...