paper-with-me

홈 › Papers

Causal Imitation Learning under Temporally Correlated Noise

2022-02-02 · Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions. When noise affects multiple timesteps of recorded data, it can manifest as spurious correlations between states and actions that a learner might latch on to, leading to poor policy performance. To break up these spurious correlations, we apply modern variants of the instrumental variable regression (IVR) technique of econometrics, enabling us to recover the underlying policy without requiring access to an interactive expert. In particular, we present two techniques, one of a generative-modeling flavor (DoubIL) that can utilize access to a simulator, and one of a game-theoretic flavor (ResiduIL) that can be run entirely offline. We find both of our algorithms compare favorably to behavioral cloning on simulated control tasks.

📄 PDF Abstract BibTeX arXiv:2202.01312

Code (1)

gkswamy98/causal_il 공식 구현 pytorch

Tasks

EconometricsImitation Learning

Similar Papers 제목 키워드 기반

Differentially Private Online Federated Learning with Correlated Noise

2024-03-25 · Jiaojiao Zhang, Linglingzhi Zhu, Mikael Johansson

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenge…

Federated Learning

Infant Spontaneous Movement Noise Improves Exploration in Deep RL

2026-06-15 · Francisco M. López, Markus R. Ernst, Francisco Cruz, Matej Hoffmann 외 arxiv

Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However, recent works show that temporally correlated colored noise can improve exploration efficiency by pr…

Reinforcement Learning

Locally Differentially Private Online Federated Learning With Correlated Noise

2024-11-27 · Jiaojiao Zhang, Linglingzhi Zhu, Dominik Fay, Mikael Johansson

We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correla…

Federated Learning

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

2026-05-12 · Puyu Wang, Jan Schuchardt, Nikita Kalinin, Junyu Zhou 외 arxiv

We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian …

Causal Discovery with Mixed Latent Confounding via Precision Decomposition

2025-12-31 · Amir Asiaee, Samhita Pal, James O'quinn, James P. Long arxiv

We study causal discovery from observational data in linear Gaussian systems affected by \emph{mixed latent confounding}, where some unobserved factors act broadly across many variables while others influence only small …