paper-with-me

홈 › Papers

Causal Action Influence Aware Counterfactual Data Augmentation

2024-05-29 · Núria Armengol Urpí, Marco Bagatella, Marin Vlastelica, Georg Martius

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online environment interactions. By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping $\it{action}$-unaffected parts of the state-space between independent trajectories in the dataset. We empirically show that this leads to a substantial increase in robustness of offline learning algorithms against distributional shift.

📄 PDF Abstract BibTeX arXiv:2405.18917

Code (1)

martius-lab/caiac 공식 구현 pytorch

Tasks

counterfactualCounterfactual ReasoningData Augmentation

Similar Papers 제목 키워드 기반

Multi-Agent Causal Reasoning for Suicide Ideation Detection Through Online Conversations

2026-02-27 · Jun Li, Xiangmeng Wang, Haoyang Li, Yifei Yan 외 arxiv

Suicide remains a pressing global public health concern. While social media platforms offer opportunities for early risk detection through online conversation trees, existing approaches face two major limitations: (1) Th…

Decision Making

Counterfactual Influence in Markov Decision Processes

2024-02-13 · Milad Kazemi, Jessica Lally, Ekaterina Tishchenko, Hana Chockler 외

Our work addresses a fundamental problem in the context of counterfactual inference for Markov Decision Processes (MDPs). Given an MDP path $\tau$, this kind of inference allows us to derive counterfactual paths $\tau'$ …

counterfactualCounterfactual Inference

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

2026-04-05 · Mohammad Hossein Chinaei arxiv

Tool-calling LLM agents can read private data, invoke external services, and trigger real-world actions, creating a security problem at the point of tool execution. We identify a denial-feedback leakage pattern, which we…

Estimating Online Influence Needs Causal Modeling! Counterfactual Analysis of Social Media Engagement

2025-05-25 · Lin Tian, Marian-Andrei Rizoiu

Understanding true influence in social media requires distinguishing correlation from causation--particularly when analyzing misinformation spread. While existing approaches focus on exposure metrics and network structur…

Causal InferencecounterfactualMisinformation

Generating Causal Temporal Interaction Graphs for Counterfactual Validation of Temporal Link Prediction

2026-02-02 · Aniq Ur Rahman, Justin P. Coon arxiv

Temporal link prediction (TLP) models are commonly evaluated based on predictive accuracy, yet such evaluations do not assess whether these models capture the causal mechanisms that govern temporal interactions. In this …

Link Prediction