Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation
arXiv: Learning, Volume abs/1809.10658, 2018.
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 ans...More
PPT (Upload PPT)