Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913383067942912 |
|---|---|
| author | Triantafyllou, Stelios Sukovic, Aleksa Mandal, Debmalya Radanovic, Goran |
| author_facet | Triantafyllou, Stelios Sukovic, Aleksa Mandal, Debmalya Radanovic, Goran |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_11334 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs Triantafyllou, Stelios Sukovic, Aleksa Mandal, Debmalya Radanovic, Goran Artificial Intelligence 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. |
| title | Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2310.11334 |