Learning Open Domain Multi-hop Search Using Reinforcement Learning

2022-05-30 · NAACL (SUKI) 2022 7 · Enrique Noriega-Atala, Mihai Surdeanu, Clayton T. Morrison

We propose a method to teach an automated agent to learn how to search for multi-hop paths of relations between entities in an open domain. The method learns a policy for directing existing information retrieval and machine reading resources to focus on relevant regions of a corpus. The approach formulates the learning problem as a Markov decision process with a state representation that encodes the dynamics of the search process and a reward structure that minimizes the number of documents that must be processed while still finding multi-hop paths. We implement the method in an actor-critic reinforcement learning algorithm and evaluate it on a dataset of search problems derived from a subset of English Wikipedia. The algorithm finds a family of policies that succeeds in extracting the desired information while processing fewer documents compared to several baseline heuristic algorithms.

📄 PDF Abstract BibTeX arXiv:2205.15281

Code (0)

등록된 구현이 없습니다.

Tasks

Information Retrieval Reading Comprehension reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Retrieval

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

2025-11-24 · Rulin Shao, Akari Asai, Shannon Zejiang Shen, Hamish Ivison 외 arxiv

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with…

Reinforcement Learning Fact Checking

Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models

2021-02-19 · Andreas Schuderer, Stefano Bromuri, Marko van Eekelen

Reinforcement learning (RL) is one of the most active fields of AI research. Despite the interest demonstrated by the research community in reinforcement learning, the development methodology still lags behind, with a se…

OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Deep Reinforcement Learning Radio Control and Signal Detection with KeRLym, a Gym RL Agent

2016-05-30 · Timothy J. O'Shea, T. Charles Clancy

This paper presents research in progress investigating the viability and adaptation of reinforcement learning using deep neural network based function approximation for the task of radio control and signal detection in t…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

OR-Gym: A Reinforcement Learning Library for Operations Research Problems

2020-08-14 · Christian D. Hubbs, Hector D. Perez, Owais Sarwar, Nikolaos V. Sahinidis 외

Reinforcement learning (RL) has been widely applied to game-playing and surpassed the best human-level performance in many domains, yet there are few use-cases in industrial or commercial settings. We introduce OR-Gym, a…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MMM: Multilingual Mutual Reinforcement Effect Mix Datasets & Test with Open-domain Information Extraction Large Language Models

2024-07-15 · Chengguang Gan, Sunbowen Lee, Qingyu Yin, Xinyang He 외

The Mutual Reinforcement Effect (MRE) represents a promising avenue in information extraction and multitasking research. Nevertheless, its applicability has been constrained due to the exclusive availability of MRE mix d…

Language Modeling Language Modelling Large Language Model named-entity-recognition+5