Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs

Stelios Triantafyllou, Aleksa Sukovic, Debmalya Mandal, Goran Radanovic
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:48578-48607, 2024.

Abstract

Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents’ contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent’s action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents’ actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent’s action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-triantafyllou24a, title = {Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent {MDP}s}, author = {Triantafyllou, Stelios and Sukovic, Aleksa and Mandal, Debmalya and Radanovic, Goran}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {48578--48607}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/triantafyllou24a/triantafyllou24a.pdf}, url = {https://proceedings.mlr.press/v235/triantafyllou24a.html}, abstract = {Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents’ contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent’s action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents’ actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent’s action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.} }
Endnote
%0 Conference Paper %T Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs %A Stelios Triantafyllou %A Aleksa Sukovic %A Debmalya Mandal %A Goran Radanovic %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-triantafyllou24a %I PMLR %P 48578--48607 %U https://proceedings.mlr.press/v235/triantafyllou24a.html %V 235 %X Establishing causal relationships between actions and outcomes is fundamental for accountable multi-agent decision-making. However, interpreting and quantifying agents’ contributions to such relationships pose significant challenges. These challenges are particularly prominent in the context of multi-agent sequential decision-making, where the causal effect of an agent’s action on the outcome depends on how other agents respond to that action. In this paper, our objective is to present a systematic approach for attributing the causal effects of agents’ actions to the influence they exert on other agents. Focusing on multi-agent Markov decision processes, we introduce agent-specific effects (ASE), a novel causal quantity that measures the effect of an agent’s action on the outcome that propagates through other agents. We then turn to the counterfactual counterpart of ASE (cf-ASE), provide a sufficient set of conditions for identifying cf-ASE, and propose a practical sampling-based algorithm for estimating it. Finally, we experimentally evaluate the utility of cf-ASE through a simulation-based testbed, which includes a sepsis management environment.
APA
Triantafyllou, S., Sukovic, A., Mandal, D. & Radanovic, G.. (2024). Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:48578-48607 Available from https://proceedings.mlr.press/v235/triantafyllou24a.html.

Related Material