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

arXiv: https://arxiv.org/abs/2310.11334 · HTML: https://mlsanity.com/paper/2310.11334/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 54 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Explainable Reinforcement Learning Through a Causal Lens](https://mlsanity.com/paper/1905.10958/) (2019)
- [Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models](https://mlsanity.com/paper/1905.05824/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search](https://mlsanity.com/paper/1811.06272/) (2018)
- [Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation](https://mlsanity.com/paper/2012.09092/) (2020)
- [Agent Incentives: A Causal Perspective](https://mlsanity.com/paper/2102.01685/) (2021)
- [Counterfactual Identifiability of Bijective Causal Models](https://mlsanity.com/paper/2302.02228/) (2023)
- [Characterizing Manipulation from AI Systems](https://mlsanity.com/paper/2303.09387/) (2023)
- [Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity](https://mlsanity.com/paper/1908.11071/) (2019)
- [Nested Counterfactual Identification from Arbitrary Surrogate Experiments](https://mlsanity.com/paper/2107.03190/) (2021)
- [Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility](https://mlsanity.com/paper/1810.05903/) (2018)
- [Counterfactual harm](https://mlsanity.com/paper/2204.12993/) (2022)
- [Feature-Based Q-Learning for Two-Player Stochastic Games](https://mlsanity.com/paper/1906.00423/) (2019)
- [Game-Theoretic Modeling of Human Adaptation in Human-Robot Collaboration](https://mlsanity.com/paper/1701.07790/) (2017)
- [Path-Specific Objectives for Safer Agent Incentives](https://mlsanity.com/paper/2204.10018/) (2022)
- [Learning to Collaborate in Markov Decision Processes](https://mlsanity.com/paper/1901.08029/) (2019)
- [On Blame Attribution for Accountable Multi-Agent Sequential Decision Making](https://mlsanity.com/paper/2107.11927/) (2021)
- [Finding Counterfactually Optimal Action Sequences in Continuous State Spaces](https://mlsanity.com/paper/2306.03929/) (2023)
- [Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes](https://mlsanity.com/paper/2204.00302/) (2022)
- [Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention](https://mlsanity.com/paper/2111.05819/) (2021)
- [Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs](https://mlsanity.com/paper/2302.12676/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.14892/) (2026)

## Abstract (arXiv)

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.