arXiv subjects

Goran Radanovic

Publications and source records attributed to Goran Radanovic.

34 records · Page 2Linked to original sources

arXiv2022

Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes

Actual causality and a closely related concept of responsibility attribution are central to accountable decision making. Actual causality focuses on specific outcomes and aims to identify decisions (actions) that were critical in realizing an outcome of interest. Responsibility attribution is complementary and aims to identify the extent to which decision makers (agents) are responsible for this outcome. In this paper, we study these concepts under a widely used framework for multi-agent sequential decision making under uncertainty: decentralized partially observable Markov decision processes (Dec-POMDPs). Following recent works in RL that show correspondence between POMDPs and Structural Causal Models (SCMs), we first establish a connection between Dec-POMDPs and SCMs. This connection enables us to utilize a language for describing actual causality from prior work and study existing definitions of actual causality in Dec-POMDPs. Given that some of the well-known definitions may lead to counter-intuitive actual causes, we introduce a novel definition that more explicitly accounts for causal dependencies between agents' actions. We then turn to responsibility attribution based on actual causality, where we argue that in ascribing responsibility to an agent it is important to consider both the number of actual causes in which the agent participates, as well as its ability to manipulate its own degree of responsibility. Motivated by these arguments we introduce a family of responsibility attribution methods that extends prior work, while accounting for the aforementioned considerations. Finally, through a simulation-based experiment, we compare different definitions of actual causality and responsibility attribution methods. The empirical results demonstrate the qualitative difference between the considered definitions of actual causality and their impact on attributed responsibility.

cs.AI↗

arXiv2022

Bayesian Persuasion in Sequential Decision-Making

We study a dynamic model of Bayesian persuasion in sequential decision-making settings. An informed principal observes an external parameter of the world and advises an uninformed agent about actions to take over time. The agent takes actions in each time step based on the current state, the principal's advice/signal, and beliefs about the external parameter. The action of the agent updates the state according to a stochastic process. The model arises naturally in many applications, e.g., an app (the principal) can advice the user (the agent) on possible choices between actions based on additional real-time information the app has. We study the problem of designing a signaling strategy from the principal's point of view. We show that the principal has an optimal strategy against a myopic agent, who only optimizes their rewards locally, and the optimal strategy can be computed in polynomial time. In contrast, it is NP-hard to approximate an optimal policy against a far-sighted agent. Further, if the principal has the power to threaten the agent by not providing future signals, then we can efficiently compute a threat-based strategy. This strategy guarantees the principal's payoff as if playing against an agent who is far-sighted but myopic to future signals.

cs.GT↗

arXiv2022

On Blame Attribution for Accountable Multi-Agent Sequential Decision Making

Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of cooperative multi-agent sequential decision making. As a particular setting of interest, we focus on cooperative decision making formalized by Multi-Agent Markov Decision Processes (MMDPs), and we analyze different blame attribution methods derived from or inspired by existing concepts in cooperative game theory. We formalize desirable properties of blame attribution in the setting of interest, and we analyze the relationship between these properties and the studied blame attribution methods. Interestingly, we show that some of the well known blame attribution methods, such as Shapley value, are not performance-incentivizing, while others, such as Banzhaf index, may over-blame agents. To mitigate these value misalignment and fairness issues, we introduce a novel blame attribution method, unique in the set of properties it satisfies, which trade-offs explanatory power (by under-blaming agents) for the aforementioned properties. We further show how to account for uncertainty about agents' decision making policies, and we experimentally: a) validate the qualitative properties of the studied blame attribution methods, and b) analyze their robustness to uncertainty.

cs.AI↗

arXiv2022

Admissible Policy Teaching through Reward Design

We study reward design strategies for incentivizing a reinforcement learning agent to adopt a policy from a set of admissible policies. The goal of the reward designer is to modify the underlying reward function cost-efficiently while ensuring that any approximately optimal deterministic policy under the new reward function is admissible and performs well under the original reward function. This problem can be viewed as a dual to the problem of optimal reward poisoning attacks: instead of forcing an agent to adopt a specific policy, the reward designer incentivizes an agent to avoid taking actions that are inadmissible in certain states. Perhaps surprisingly, and in contrast to the problem of optimal reward poisoning attacks, we first show that the reward design problem for admissible policy teaching is computationally challenging, and it is NP-hard to find an approximately optimal reward modification. We then proceed by formulating a surrogate problem whose optimal solution approximates the optimal solution to the reward design problem in our setting, but is more amenable to optimization techniques and analysis. For this surrogate problem, we present characterization results that provide bounds on the value of the optimal solution. Finally, we design a local search algorithm to solve the surrogate problem and showcase its utility using simulation-based experiments.

cs.LG↗

arXiv2021

Reinforcement Learning for Education: Opportunities and Challenges

This survey article has grown out of the RL4ED workshop organized by the authors at the Educational Data Mining (EDM) 2021 conference. We organized this workshop as part of a community-building effort to bring together researchers and practitioners interested in the broad areas of reinforcement learning (RL) and education (ED). This article aims to provide an overview of the workshop activities and summarize the main research directions in the area of RL for ED.

cs.LG↗

arXiv2021

Defense Against Reward Poisoning Attacks in Reinforcement Learning

We study defense strategies against reward poisoning attacks in reinforcement learning. As a threat model, we consider attacks that minimally alter rewards to make the attacker's target policy uniquely optimal under the poisoned rewards, with the optimality gap specified by an attack parameter. Our goal is to design agents that are robust against such attacks in terms of the worst-case utility w.r.t. the true, unpoisoned, rewards while computing their policies under the poisoned rewards. We propose an optimization framework for deriving optimal defense policies, both when the attack parameter is known and unknown. Moreover, we show that defense policies that are solutions to the proposed optimization problems have provable performance guarantees. In particular, we provide the following bounds with respect to the true, unpoisoned, rewards: a) lower bounds on the expected return of the defense policies, and b) upper bounds on how suboptimal these defense policies are compared to the attacker's target policy. We conclude the paper by illustrating the intuitions behind our formal results, and showing that the derived bounds are non-trivial.

cs.LG↗

arXiv2021

Diversity in News Recommendations

News diversity in the media has for a long time been a foundational and uncontested basis for ensuring that the communicative needs of individuals and society at large are met. Today, people increasingly rely on online content and recommender systems to consume information challenging the traditional concept of news diversity. In addition, the very concept of diversity, which differs between disciplines, will need to be re-evaluated requiring a interdisciplinary investigation, which requires a new level of mutual cooperation between computer scientists, social scientists, and legal scholars. Based on the outcome of a multidisciplinary workshop, we have the following recommendations, directed at researchers, funders, legislators, regulators, and the media industry: 1. Do more research on news recommenders and diversity. 2. Create a safe harbor for academic research with industry data. 3. Optimize the role of public values in news recommenders. 4. Create a meaningful governance framework. 5. Fund a joint lab to spearhead the needed interdisciplinary research, boost practical innovation, develop. reference solutions, and transfer insights into practice.

cs.CY↗

arXiv2020

Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes reward in infinite-horizon problem settings. The attacker can manipulate the rewards and the transition dynamics in the learning environment at training-time, and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an optimal stealthy attack for different measures of attack cost. We provide lower/upper bounds on the attack cost, and instantiate our attacks in two settings: (i) an offline setting where the agent is doing planning in the poisoned environment, and (ii) an online setting where the agent is learning a policy with poisoned feedback. Our results show that the attacker can easily succeed in teaching any target policy to the victim under mild conditions and highlight a significant security threat to reinforcement learning agents in practice.

cs.LG↗

arXiv2020

Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning

We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \emph{optimal stealthy attack} for different measures of attack cost. We provide sufficient technical conditions under which the attack is feasible and provide lower/upper bounds on the attack cost. We instantiate our attacks in two settings: (i) an \emph{offline} setting where the agent is doing planning in the poisoned environment, and (ii) an \emph{online} setting where the agent is learning a policy using a regret-minimization framework with poisoned feedback. Our results show that the attacker can easily succeed in teaching any target policy to the victim under mild conditions and highlight a significant security threat to reinforcement learning agents in practice.

cs.LG↗

arXiv2019

Learning to Collaborate in Markov Decision Processes

We consider a two-agent MDP framework where agents repeatedly solve a task in a collaborative setting. We study the problem of designing a learning algorithm for the first agent (A1) that facilitates a successful collaboration even in cases when the second agent (A2) is adapting its policy in an unknown way. The key challenge in our setting is that the first agent faces non-stationarity in rewards and transitions because of the adaptive behavior of the second agent. We design novel online learning algorithms for agent A1 whose regret decays as $O(T^{\max\{1-\frac{3}{7} \cdot α, \frac{1}{4}\}})$ with $T$ learning episodes provided that the magnitude of agent A2's policy changes between any two consecutive episodes are upper bounded by $O(T^{-α})$. Here, the parameter $α$ is assumed to be strictly greater than $0$, and we show that this assumption is necessary provided that the learning parity with noise problem is computationally hard. We show that sub-linear regret of agent A1 further implies near-optimality of the agents' joint return for MDPs that manifest the properties of a smooth game.

cs.LG↗

arXiv2019

How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness

What is the best way to define algorithmic fairness? While many definitions of fairness have been proposed in the computer science literature, there is no clear agreement over a particular definition. In this work, we investigate ordinary people's perceptions of three of these fairness definitions. Across two online experiments, we test which definitions people perceive to be the fairest in the context of loan decisions, and whether fairness perceptions change with the addition of sensitive information (i.e., race of the loan applicants). Overall, one definition (calibrated fairness) tends to be more preferred than the others, and the results also provide support for the principle of affirmative action.

cs.AI↗

arXiv2018

Bayesian fairness

We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate parameter uncertainty, hence we introduce the notion of {\em Bayesian fairness} as a suitable candidate for fair decision rules. Using balance, a definition of fairness introduced by Kleinberg et al (2016), we show how a Bayesian perspective can lead to well-performing, fair decision rules even under high uncertainty.

cs.LG↗

arXiv2017

Partial Truthfulness in Minimal Peer Prediction Mechanisms with Limited Knowledge

We study minimal single-task peer prediction mechanisms that have limited knowledge about agents' beliefs. Without knowing what agents' beliefs are or eliciting additional information, it is not possible to design a truthful mechanism in a Bayesian-Nash sense. We go beyond truthfulness and explore equilibrium strategy profiles that are only partially truthful. Using the results from the multi-armed bandit literature, we give a characterization of how inefficient these equilibria are comparing to truthful reporting. We measure the inefficiency of such strategies by counting the number of dishonest reports that any minimal knowledge-bounded mechanism must have. We show that the order of this number is $Θ(\log n)$, where $n$ is the number of agents, and we provide a peer prediction mechanism that achieves this bound in expectation.

cs.GT↗

arXiv2017

Information Gathering with Peers: Submodular Optimization with Peer-Prediction Constraints

We study a problem of optimal information gathering from multiple data providers that need to be incentivized to provide accurate information. This problem arises in many real world applications that rely on crowdsourced data sets, but where the process of obtaining data is costly. A notable example of such a scenario is crowd sensing. To this end, we formulate the problem of optimal information gathering as maximization of a submodular function under a budget constraint, where the budget represents the total expected payment to data providers. Contrary to the existing approaches, we base our payments on incentives for accuracy and truthfulness, in particular, {\em peer-prediction} methods that score each of the selected data providers against its best peer, while ensuring that the minimum expected payment is above a given threshold. We first show that the problem at hand is hard to approximate within a constant factor that is not dependent on the properties of the payment function. However, for given topological and analytical properties of the instance, we construct two greedy algorithms, respectively called PPCGreedy and PPCGreedyIter, and establish theoretical bounds on their performance w.r.t. the optimal solution. Finally, we evaluate our methods using a realistic crowd sensing testbed.

cs.GT↗

arXiv2017

Calibrated Fairness in Bandits

We study fairness within the stochastic, \emph{multi-armed bandit} (MAB) decision making framework. We adapt the fairness framework of "treating similar individuals similarly" to this setting. Here, an `individual' corresponds to an arm and two arms are `similar' if they have a similar quality distribution. First, we adopt a {\em smoothness constraint} that if two arms have a similar quality distribution then the probability of selecting each arm should be similar. In addition, we define the {\em fairness regret}, which corresponds to the degree to which an algorithm is not calibrated, where perfect calibration requires that the probability of selecting an arm is equal to the probability with which the arm has the best quality realization. We show that a variation on Thompson sampling satisfies smooth fairness for total variation distance, and give an $\tilde{O}((kT)^{2/3})$ bound on fairness regret. This complements prior work, which protects an on-average better arm from being less favored. We also explain how to extend our algorithm to the dueling bandit setting.

cs.LG↗

arXiv2017

Peer Truth Serum: Incentives for Crowdsourcing Measurements and Opinions

Modern decision making tools are based on statistical analysis of abundant data, which is often collected by querying multiple individuals. We consider data collection through crowdsourcing, where independent and self-interested agents, non-experts, report measurements, such as sensor readings, opinions, such as product reviews, or answers to human intelligence tasks. Since the accuracy of information is positively correlated with the effort invested in obtaining it, self-interested agents tend to report low-quality data. Therefore, there is a need for incentives that cover the cost of effort, while discouraging random reports. We propose a novel incentive mechanism called Peer Truth Serum that encourages truthful and accurate reporting, showing that it is the unique mechanism to satisfy a combination of desirable properties.

cs.GT↗