Actual Causality and Responsibility Attribution in Decentralized
Partially Observable Markov Decision Processes
- URL: http://arxiv.org/abs/2204.00302v1
- Date: Fri, 1 Apr 2022 09:22:58 GMT
- Title: Actual Causality and Responsibility Attribution in Decentralized
Partially Observable Markov Decision Processes
- Authors: Stelios Triantafyllou, Adish Singla, Goran Radanovic
- Abstract summary: We study these concepts under a widely used framework for multi-agent sequential decision making under uncertainty.
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.
- Score: 22.408657774650358
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning [70.16523526957162]
Understanding commonsense causality helps people understand the principles of the real world better.
Despite its significance, a systematic exploration of this topic is notably lacking.
Our work aims to provide a systematic overview, update scholars on recent advancements, and provide a pragmatic guide for beginners.
arXiv Detail & Related papers (2024-06-27T16:30:50Z) - A Semantic Approach to Decidability in Epistemic Planning (Extended
Version) [72.77805489645604]
We use a novel semantic approach to achieve decidability.
Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity.
We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
arXiv Detail & Related papers (2023-07-28T11:26:26Z) - Learning Causally Disentangled Representations via the Principle of Independent Causal Mechanisms [17.074858228123706]
We propose a framework for learning causally disentangled representations supervised by causally related observed labels.
We show that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation.
arXiv Detail & Related papers (2023-06-02T00:28:48Z) - Towards Computationally Efficient Responsibility Attribution in
Decentralized Partially Observable MDPs [5.825190876052148]
Responsibility attribution is a key concept of accountable multi-agent decision making.
We introduce a Monte Carlo Tree Search (MCTS) type of method which efficiently approximates the agents' degrees of responsibility.
We experimentally evaluate the efficacy of our algorithm through a simulation-based test-bed.
arXiv Detail & Related papers (2023-02-24T14:56:25Z) - Phenomenological Causality [14.817342045377842]
We propose a notion of 'phenomenological causality' whose basic concept is a set of elementary actions.
We argue that it is consistent with the causal Markov condition when the system under consideration interacts with other variables that control the elementary actions.
arXiv Detail & Related papers (2022-11-15T13:05:45Z) - Application of Causal Inference to Analytical Customer Relationship
Management in Banking and Insurance [6.228766191647919]
In statistics, causality has been studied and applied for many years, but not in great detail in artificial intelligence (AI)
In this study, we employed the principles of causal inference to provide explainability for solving the analytical customer relationship management problems.
Good quality counterfactuals were generated for the loan default, insurance fraud detection, and credit card fraud detection datasets.
arXiv Detail & Related papers (2022-08-19T05:57:58Z) - Causal Fairness Analysis [68.12191782657437]
We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings.
The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms.
Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
arXiv Detail & Related papers (2022-07-23T01:06:34Z) - On Blame Attribution for Accountable Multi-Agent Sequential Decision
Making [29.431349181232203]
We study blame attribution in the context of cooperative multi-agent sequential decision making.
We show that some of the well known blame attribution methods, such as Shapley value, are not performance-incentivizing.
We introduce a novel blame attribution method, unique in the set of properties it satisfies.
arXiv Detail & Related papers (2021-07-26T02:22:23Z) - Everything Has a Cause: Leveraging Causal Inference in Legal Text
Analysis [62.44432226563088]
Causal inference is the process of capturing cause-effect relationship among variables.
We propose a novel Graph-based Causal Inference framework, which builds causal graphs from fact descriptions without much human involvement.
We observe that the causal knowledge contained in GCI can be effectively injected into powerful neural networks for better performance and interpretability.
arXiv Detail & Related papers (2021-04-19T16:13:10Z) - Learning Causal Semantic Representation for Out-of-Distribution
Prediction [125.38836464226092]
We propose a Causal Semantic Generative model (CSG) based on a causal reasoning so that the two factors are modeled separately.
We show that CSG can identify the semantic factor by fitting training data, and this semantic-identification guarantees the boundedness of OOD generalization error.
arXiv Detail & Related papers (2020-11-03T13:16:05Z) - Thinking About Causation: A Causal Language with Epistemic Operators [58.720142291102135]
We extend the notion of a causal model with a representation of the state of an agent.
On the side of the object language, we add operators to express knowledge and the act of observing new information.
We provide a sound and complete axiomatization of the logic, and discuss the relation of this framework to causal team semantics.
arXiv Detail & Related papers (2020-10-30T12:16:45Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.