English
Related papers

Related papers: Woulda, Coulda, Shoulda: Counterfactually-Guided P…

200 papers

Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their interactions are often sparse, and the…

Machine Learning · Computer Science 2020-12-07 Silviu Pitis , Elliot Creager , Animesh Garg

We present a new method for estimating the expected return of a POMDP from experience. The method does not assume any knowledge of the POMDP and allows the experience to be gathered from an arbitrary sequence of policies. The return is…

Artificial Intelligence · Computer Science 2013-01-14 Christian R. Shelton

General Value Function (GVF) is a powerful tool to represent both the {\em predictive} and {\em retrospective} knowledge in reinforcement learning (RL). In practice, often multiple interrelated GVFs need to be evaluated jointly with…

Machine Learning · Computer Science 2021-07-07 Tengyu Xu , Zhuoran Yang , Zhaoran Wang , Yingbin Liang

Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Xiaoyang Tan , Zhe Wu , Junliang Xing

In this paper, we address the limitations of traditional teacher-student models, imitation learning, and behaviour cloning in the context of Autonomous/Automated Driving Systems (ADS), where these methods often struggle with incomplete…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Amir Samadi , Konstantinos Koufos , Kurt Debattista , Mehrdad Dianati

Algorithms are commonly used to predict outcomes under a particular decision or intervention, such as predicting whether an offender will succeed on parole if placed under minimal supervision. Generally, to learn such counterfactual…

Machine Learning · Statistics 2021-04-19 Amanda Coston , Edward H. Kennedy , Alexandra Chouldechova

Being able to reason about how one's behaviour can affect the behaviour of others is a core skill required of intelligent driving agents. Despite this, the state of the art struggles to meet the need of agents to discover causal links…

Robotics · Computer Science 2024-03-07 Rhys Howard , Lars Kunze

In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally leads to distribution shift between the behavior policy and the target policy being trained - requiring…

Machine Learning · Computer Science 2024-04-10 Matthew Thomas Jackson , Michael Tryfan Matthews , Cong Lu , Benjamin Ellis , Shimon Whiteson , Jakob Foerster

Offline reinforcement learning enables agents to leverage large pre-collected datasets of environment transitions to learn control policies, circumventing the need for potentially expensive or unsafe online data collection. Significant…

Machine Learning · Computer Science 2022-03-17 Cong Lu , Philip J. Ball , Jack Parker-Holder , Michael A. Osborne , Stephen J. Roberts

We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a…

Robotics · Computer Science 2022-03-01 Jun Jin , Daniel Graves , Cameron Haigh , Jun Luo , Martin Jagersand

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent…

Machine Learning · Computer Science 2024-06-27 Jeongyeol Kwon , Shie Mannor , Constantine Caramanis , Yonathan Efroni

Counterfactual inference considers a hypothetical intervention in a parallel world that shares some evidence with the factual world. If the evidence specifies a conditional distribution on a manifold, counterfactuals may be analytically…

Machine Learning · Statistics 2024-07-03 Juha Karvanen , Santtu Tikka , Matti Vihola

Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires…

Machine Learning · Computer Science 2016-02-17 Tianhao Zhang , Gregory Kahn , Sergey Levine , Pieter Abbeel

Learning causal relationships in high-dimensional data (images, videos) is a hard task, as they are often defined on low dimensional manifolds and must be extracted from complex signals dominated by appearance, lighting, textures and also…

Computer Vision and Pattern Recognition · Computer Science 2022-06-30 Steeven Janny , Fabien Baradel , Natalia Neverova , Madiha Nadri , Greg Mori , Christian Wolf

We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are…

Machine Learning · Computer Science 2025-12-09 Nishanth Venkatesh , Andreas A. Malikopoulos

This paper prescribes a suite of techniques for off-policy Reinforcement Learning (RL) that simplify the training process and reduce the sample complexity. First, we show that simple Deterministic Policy Gradient works remarkably well as…

Machine Learning · Computer Science 2020-06-30 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with human reasoning.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Syed Ali Tariq , Tehseen Zia

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the…

Machine Learning · Computer Science 2022-10-04 Kevin Xia , Yushu Pan , Elias Bareinboim