paper-with-me

Papers

Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning

2019-11-25 · Mark Edmonds, Xiaojian Ma, Siyuan Qi, Yixin Zhu, Hongjing Lu, Song-Chun Zhu

Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains, and (ii) the behavior of specific features of the environment remain constant across domains. We adopt a Bayesian perspective of causal theory induction and use these theories to transfer knowledge between environments. Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment. A hierarchy of Bayesian structures is used to model abstract-level structural causal knowledge, and an instance-level associative learning scheme learns which specific objects can be used to induce state changes through interaction. This model-learning scheme is then integrated with a model-based planner to achieve a task in the OpenLock environment, a virtual ``escape room'' with a complex hierarchy that requires agents to reason about an abstract, generalized causal structure. We compare performances against a set of predominate model-free reinforcement learning(RL) algorithms. RL agents showed poor ability transferring learned knowledge across different trials. Whereas the proposed model revealed similar performance trends as human learners, and more importantly, demonstrated transfer behavior across trials and learning situations.

📄 PDF Abstract BibTeX arXiv:1911.11185

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningReinforcement Learning (RL)Transfer Learning

Similar Papers 제목 키워드 기반

Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization

2022-02-25 · Weijia Zhang, Xuanhui Zhang, Han-Wen Deng, Min-Ling Zhang

Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorit…

Multiple Instance LearningOut-of-Distribution GeneralizationRepresentation Learning

A unified theory of information transfer and causal relation

2022-04-21 · Yang Tian, Hedong Hou, Yaoyuan Wang, Ziyang Zhang 외

Information transfer between coupled stochastic dynamics, measured by transfer entropy and information flow, is suggested as a physical process underlying the causal relation of systems. While information transfer analys…

Causal InferenceRelation

Interpreting Low-level Vision Models with Causal Effect Maps

2024-07-29 · JinFan Hu, Jinjin Gu, Shiyao Yu, Fanghua Yu 외

Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep models is beneficial for both network design …

DenoisingDiagnosticImage Denoising

Graphical Models for Decision-Making: Integrating Causality and Game Theory

2025-04-16 · Maarten C. Vonk, Mauricio Gonzalez Soto, Anna V. Kononova

Causality and game theory are two influential fields that contribute significantly to decision-making in various domains. Causality defines and models causal relationships in complex policy problems, while game theory pr…

Decision Making

Using causal abstractions to accelerate decision-making in complex bandit problems

2025-09-04 · Joel Dyer, Nicholas Bishop, Anisoara Calinescu, Michael Wooldridge 외 arxiv

Although real-world decision-making problems can often be encoded as causal multi-armed bandits (CMABs) at different levels of abstraction, a general methodology exploiting the information and computational advantages of…

Multi-Armed Bandits