Related papers: (Machine) Learning What Policies Value

Recent work has shown that reinforcement learning agents can develop policies that exploit spurious correlations between rewards and observations. This phenomenon, known as policy confounding, arises because the agent's policy influences…

Using high-quality nation-wide social security data combined with machine learning tools, we develop predictive models of income support receipt intensities for any payment enrolee in the Australian social security system between 2014 and…

When some resources are to be distributed among a set of agents following egalitarian social welfare, the goal is to maximize the utility of the agent whose utility turns out to be minimal. In this context, agents can have an incentive to…

In prediction-based decision-making systems, different perspectives can be at odds: The short-term business goals of the decision makers are often in conflict with the decision subjects' wish to be treated fairly. Balancing these two…

We devise and analyze algorithms for the empirical policy evaluation problem in reinforcement learning. Our algorithms explore backward from high-cost states to find high-value ones, in contrast to forward approaches that work forward from…

The advent of powerful prediction algorithms led to increased automation of high-stake decisions regarding the allocation of scarce resources such as government spending and welfare support. This automation bears the risk of perpetuating…

We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models. Our hypothesis is: Biased Models have Biased Explanations. To establish that, we first translate existing…

Machine learning algorithms are now capable of performing evaluations previously conducted by human experts (e.g., medical diagnoses). How should we conceptualize the difference between evaluation by humans and by algorithms, and when…

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards:…

Multiple lines of evidence suggest that predictive models may benefit from algorithmic triage. Under algorithmic triage, a predictive model does not predict all instances but instead defers some of them to human experts. However, the…

A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an ``optimal'' predicted outcome distribution according to some…

Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of…

The last decade has seen a revolution in the theory and application of machine learning and pattern recognition. Through these advancements, variable ranking has emerged as an active and growing research area and it is now beginning to be…

A researcher allocates a budget of informative tests across multiple unknown attributes to influence a decision-maker. We derive the researcher's equilibrium learning strategy by solving an auxiliary single-player problem. The attribute…

As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. The output of an algorithm can be discriminatory for many…

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

The performance of machine learning algorithms can be considerably improved when trained over larger datasets. In many domains, such as medicine and finance, larger datasets can be obtained if several parties, each having access to limited…

Feature weighting algorithms try to solve a problem of great importance nowadays in machine learning: The search of a relevance measure for the features of a given domain. This relevance is primarily used for feature selection as feature…

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path…

It is common to compare individualized treatment rules based on the value function, which is the expected potential outcome under the treatment rule. Although the value function is not point-identified when there is unmeasured confounding,…