English
Related papers

Related papers: Provable Interactive Learning with Hindsight Instr…

200 papers

Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and…

Machine Learning · Computer Science 2018-10-08 Ofir Nachum , Shixiang Gu , Honglak Lee , Sergey Levine

Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of…

Machine Learning · Computer Science 2018-12-03 Adrian Šošić , Elmar Rueckert , Jan Peters , Abdelhak M. Zoubir , Heinz Koeppl

Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preference datasets is prohibitively expensive. \textit{This raises a…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Xiaoxuan He , Siming Fu , Wanli Li , Zhiyuan Li , Dacheng Yin , Kang Rong , Fengyun Rao , Bo Zhang

Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they…

Robotics · Computer Science 2022-01-20 Eugenio Chisari , Tim Welschehold , Joschka Boedecker , Wolfram Burgard , Abhinav Valada

For many reinforcement learning (RL) applications, specifying a reward is difficult. This paper considers an RL setting where the agent obtains information about the reward only by querying an expert that can, for example, evaluate…

Machine Learning · Computer Science 2022-02-01 David Lindner , Matteo Turchetta , Sebastian Tschiatschek , Kamil Ciosek , Andreas Krause

Effective exploration continues to be a significant challenge that prevents the deployment of reinforcement learning for many physical systems. This is particularly true for systems with continuous and high-dimensional state and action…

Machine Learning · Computer Science 2022-07-21 Trevor Ablett , Bryan Chan , Jonathan Kelly

Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem…

Machine Learning · Computer Science 2024-04-16 Mudit Verma , Katherine Metcalf

While intelligent tutoring systems (ITSs) can use information from past students to personalize instruction, each new student is unique. Moreover, the education problem is inherently difficult because the learning process is only partially…

Machine Learning · Computer Science 2025-11-20 Jeffrey Jiang , Kevin Hong , Emily Kuczynski , Gregory Pottie

We propose a new framework for imitation learning -- treating imitation as a two-player ranking-based game between a policy and a reward. In this game, the reward agent learns to satisfy pairwise performance rankings between behaviors,…

Machine Learning · Computer Science 2023-01-18 Harshit Sikchi , Akanksha Saran , Wonjoon Goo , Scott Niekum

While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly…

Information Retrieval · Computer Science 2025-05-26 Nilanjan Sinhababu , Andrew Parry , Debasis Ganguly , Pabitra Mitra

The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central…

Machine Learning · Computer Science 2024-12-17 Joar Skalse , Alessandro Abate

Recent work has questioned whether large language models (LLMs) can perform genuine in-context learning (ICL) for scientific experimental design, with prior studies suggesting that LLM-based agents exhibit no sensitivity to experimental…

When faced with accomplishing a task, human experts exhibit intentional behavior. Their unique intents shape their plans and decisions, resulting in experts demonstrating diverse behaviors to accomplish the same task. Due to the…

Machine Learning · Computer Science 2024-04-29 Sangwon Seo , Vaibhav Unhelkar

Robots learning from observations in the real world using inverse reinforcement learning (IRL) may encounter objects or agents in the environment, other than the expert, that cause nuisance observations during the demonstration. These…

Machine Learning · Computer Science 2023-05-18 Kenneth Bogert , Prashant Doshi

Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…

Machine Learning · Computer Science 2019-07-22 Vanessa Kosoy

Inverse reinforcement learning (IRL) is the problem of inferring the reward function of an agent, given its policy or observed behavior. Analogous to RL, IRL is perceived both as a problem and as a class of methods. By categorically…

Machine Learning · Computer Science 2020-11-19 Saurabh Arora , Prashant Doshi

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behaviors under ambiguity.…

Machine Learning · Computer Science 2019-09-25 Rui Chen , Wenshuo Wang , Zirui Zhao , Ding Zhao

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

Machine Learning · Computer Science 2021-03-01 Naman Agarwal , Elad Hazan , Anirudha Majumdar , Karan Singh

Incentive mechanisms for crowdsourcing are designed to incentivize financially self-interested workers to generate and report high-quality labels. Existing mechanisms are often developed as one-shot static solutions, assuming a certain…

Computer Science and Game Theory · Computer Science 2018-06-04 Zehong Hu , Yitao Liang , Yang Liu , Jie Zhang

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case…

Machine Learning · Statistics 2015-03-04 Tim van Erven , Peter Grünwald , Wouter M. Koolen , Steven de Rooij