Skip to content
Snippets Groups Projects
Select Git revision
  • ac71b6bf3efd5fc7af8bba0046fd8d903a8049ed
  • master default protected
2 results

Policy.rst

Blame
  • Code owners
    Assign users and groups as approvers for specific file changes. Learn more.
    Policy.rst 2.28 KiB

    Policy

    DeepRL Policies

    FeudalRL Policies

    Traditional Reinforcement Learning algorithms fail to scale to large domains due to the curse of dimensionality. A novel Dialogue Management architecture based on Feudal RL decomposes the decision into two steps; a first step where a master policy selects a subset of primitive actions, and a second step where a primitive action is chosen from the selected subset. The structural information included in the domain ontology is used to abstract the dialogue state space, taking the decisions at each step using different parts of the abstracted state. This, combined with an information sharing mechanism between slots, increases the scalability to large domains.

    For more information, please look at the paper Feudal Reinforcement Learning for Dialogue Management in Large Domains.