Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
By Rodrigo Nogueira, Jannis Bulian, Massimiliano Ciaramita. 2018
11 citations recorded by the source corpus.
We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong baselines, such as an ensemble of agents trained on the full data. We show that the improved performance is due to the increased diversity of reformulation strategies.
Subfields: Artificial Intelligence, Computer Science Applications, Natural Language Processing, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Zhiguo Wang
- Bing Xiang
- Ramesh Nallapati
- Xiaofei Ma
- Patrick Ng
- Mohit Bansal
- Hannaneh Hajishirzi
- Caiming Xiong
In Natural Language Processing
- Zhiguo Wang
- Ramesh Nallapati
- Bing Xiang
- Xiaofei Ma
- Patrick Ng
- Mohit Bansal
- Hannaneh Hajishirzi
- Caiming Xiong
In Reinforcement Learning
Citations in the corpus
- Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering (2019, background): “…28.7 36.6 TraCRNet (Dehghani et al., 2019) 43.2 54.0 52.9 65.1 - - - - HAS-QA (Pang et al., 2019) 43.2 48.9 62.7 68.7 63.6 68.9 - - BERT (Large) (Nogueira et al., sages with questions, aka inter-sentence matching (Wang and Jiang, 2017; Wang et al., 2016; Seo et al., 2017; Wang et al., 2017;…”