Related papers: Extracting Incentives from Black-Box Decisions
Markov decision processes are useful models of concurrency optimisation problems, but are often intractable for exhaustive verification methods. Recent work has introduced lightweight approximative techniques that sample directly from…
It is well known that options can make planning more efficient, among their many benefits. Thus far, algorithms for autonomously discovering a set of useful options were heuristic. Naturally, a principled way of finding a set of useful…
Governments are increasingly turning to algorithmic risk assessments when making important decisions, such as whether to release criminal defendants before trial. Policymakers assert that providing public servants with algorithmic advice…
AI systems increasingly support human decision-making. In many cases, despite the algorithm's superior performance, the final decision remains in human hands. For example, an AI may assist doctors in determining which diagnostic tests to…
Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans find a variety of…
Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…
Inferential decision-making algorithms typically assume that an underlying probabilistic model of decision alternatives and outcomes may be learned a priori or online. Furthermore, when applied to robots in real-world settings they often…
While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…
An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process…
Reinforcement learning (RL) is a fundamental framework for sequential decision-making, in which an agent learns an optimal policy through interactions with an unknown environment. In settings with function approximation, many existing RL…
In this paper, we model a decision-making process involving a set of interacting agents. We use Markovian opinion dynamics, where each agent switches between decisions according to a continuous time Markov chain. Existing opinion dynamics…
We study a class of sequential decision-making problems with augmented predictions, potentially provided by a machine learning algorithm. In this setting, the decision-maker receives prediction intervals for unknown parameters that become…
A broad current application of algorithms is in formal and quantitative measures of murky concepts -- like merit -- to make decisions. When people strategically respond to these sorts of evaluations in order to gain favorable decision…
Computer-aided decision making--where a human decision-maker is aided by a computational classifier in making a decision--is becoming increasingly prevalent. For instance, judges in at least nine states make use of algorithmic tools meant…
The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…
General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…
Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…
Our work aims at developing reinforcement learning algorithms that do not rely on the Markov assumption. We consider the class of Non-Markov Decision Processes where histories can be abstracted into a finite set of states while preserving…
Agents are systems that optimize an objective function in an environment. Together, the goal and the environment induce secondary objectives, incentives. Modeling the agent-environment interaction using causal influence diagrams, we can…
In human-robot collaboration, the objectives of the human are often unknown to the robot. Moreover, even assuming a known objective, the human behavior is also uncertain. In order to plan a robust robot behavior, a key preliminary question…