paper-with-me

홈 › Papers

What Would the Expert $do(\cdot)$?: Causal Imitation Learning

2021-09-29 · Gokul Swamy, Sanjiban Choudhury, Drew Bagnell, Steven Wu

We develop algorithms for imitation learning from data that was corrupted by unobserved confounders. Sources of such confounding include (a) persistent perturbations to actions or (b) the expert responding to a part of the state that the learner does not have access to. When a confounder affects multiple timesteps of recorded data, it can manifest as spurious correlations between states and actions that a learner might latch onto, leading to poor policy performance. By utilizing the effect of past states on current states, we are able to break up these spurious correlations, an application of the econometric technique of instrumental variable regression. This insight leads to two novel algorithms, one of a generative-modeling flavor ($\texttt{DoubIL}$) that can utilize access to a simulator and one of a game-theoretic flavor ($\texttt{ResiduIL}$) that can be run offline. Both approaches are able to find policies that match the result of a query to an unconfounded expert. We find both algorithms compare favorably to non-causal approaches on simulated control problems.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Similar Papers 제목 키워드 기반

New Rules for Causal Identification with Background Knowledge

2024-07-21 · Tian-Zuo Wang, Lue Tao, Zhi-Hua Zhou

Identifying causal relations is crucial for a variety of downstream tasks. In additional to observational data, background knowledge (BK), which could be attained from human expertise or experiments, is usually introduce…

Causal Identification

Teleological Inference in Structural Causal Models via Intentional Interventions

2026-03-19 · Dario Compagno, Fabio Massimo Zennaro arxiv

Structural causal models (SCMs) were conceived to formulate and answer causal questions. This paper shows that SCMs can also be used to formulate and answer teleological questions, concerning the intentions of a state-aw…

CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation

2026-04-12 · Elahe Khatibi, Ziyu Wang, Ankita Sharma, Krishnendu Chakrabarty 외 arxiv

Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and retrieval without explicit physiological…

Representation Learning

What Would pi* Do?: Imitation Learning via Off-Policy Reinforcement Learning

2018-09-27 · Siddharth Reddy, Anca D. Dragan, Sergey Levine

Learning to imitate expert actions given demonstrations containing image observations is a difficult problem in robotic control. The key challenge is generalizing behavior to out-of-distribution states that differ from t…

Imitation LearningQ-Learningreinforcement-learningReinforcement Learning (RL)

Fighting Copycat Agents in Behavioral Cloning from Observation Histories

2020-10-28 · NeurIPS 2020 12 · Chuan Wen, Jierui Lin, Trevor Darrell, Dinesh Jayaraman 외

Imitation learning trains policies to map from input observations to the actions that an expert would choose. In this setting, distribution shift frequently exacerbates the effect of misattributing expert actions to nuis…

Imitation Learning