Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userUnderstanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
155
0
0.0
(
0
)
Added by
Tom Everitt
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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 answer two fundamental questions about an agents incentives directly from the graph: (1) which nodes can the agent have an incentivize to observe, and (2) which nodes can the agent have an incentivize to control? The answers tell us which information and influence points need extra protection. For example, we may want a classifier for job applications to not use the ethnicity of the candidate, and a reinforcement learning agent not to take direct control of its reward mechanism. Different algorithms and training paradigms can lead to different causal influence diagrams, so our method can be used to identify algorithms with problematic incentives and help in designing algorithms with better incentives.
rate research
Read More
We present a framework for analysing agent incentives using causal influence diagrams. We establish that a well-known criterion for value of information is complete. We propose a new graphical criterion for value of control, establishing its soundness and completeness. We also introduce two new concepts for incentive analysis: response incentives indicate which changes in the environment affect an optimal decision, while instrumental control incentives establish whether an agent can influence its utility via a variable X. For both new concepts, we provide sound and complete graphical criteria. We show by example how these results can help with evaluating the safety and fairness of an AI system.
As machine learning systems become more powerful they also become increasingly unpredictable and opaque. Yet, finding human-understandable explanations of how they work is essential for their safe deployment. This technical report illustrates a methodology for investigating the causal mechanisms that drive the behaviour of artificial agents. Six use cases are covered, each addressing a typical question an analyst might ask about an agent. In particular, we show that each question cannot be addressed by pure observation alone, but instead requires conducting experiments with systematically chosen manipulations so as to generate the correct causal evidence.
A branch-and-bound approach to solving influ- ence diagrams has been previously proposed in the literature, but appears to have never been implemented and evaluated - apparently due to the difficulties of computing effective bounds for the branch-and-bound search. In this paper, we describe how to efficiently compute effective bounds, and we develop a practical implementa- tion of depth-first branch-and-bound search for influence diagram evaluation that outperforms existing methods for solving influence diagrams with multiple stages.
Motivated by Shannons model and recent rehabilitation of self-supervised artificial intelligence having a World Model, this paper propose an unified intelligence-communication (UIC) model for describing a single agent and any multi-agent system. Firstly, the environment is modelled as the generic communication channel between agents. Secondly, the UIC model adopts a learning-agent model for unifying several well-adopted agent architecture, e.g. rule-based agent model in complex adaptive systems, layered model for describing human-level intelligence, world-model based agent model. The model may also provide an unified approach to investigate a multi-agent system (MAS) having multiple action-perception modalities, e.g. explicitly information transfer and implicit information transfer. This treatise would be divided into three parts, and this first part provides an overview of the UIC model without introducing cumbersome mathematical analysis and optimizations. In the second part of this treatise, case studies with quantitative analysis driven by the UIC model would be provided, exemplifying the adoption of the UIC model in multi-agent system. Specifically, two representative cases would be studied, namely the analysis of a natural multi-agent system, as well as the co-design of communication, perception and action in an artificial multi-agent system. In the third part of this treatise, the paper provides further insights and future research directions motivated by the UIC model, such as unification of single intelligence and collective intelligence, a possible explanation of intelligence emergence and a dual model for agent-environment intelligence hypothesis. Notes: This paper is a Previewed Version, the extended full-version would be released after being accepted.
Which variables does an agent have an incentive to control with its decision, and which variables does it have an incentive to respond to? We formalise these incentives, and demonstrate unique graphical criteria for detecting them in any single decision causal influence diagram. To this end, we introduce structural causal influence models, a hybrid of the influence diagram and structural causal model frameworks. Finally, we illustrate how these incentives predict agent incentives in both fairness and AI safety applications.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
