Meta Dialogue Policy Learning

Understand

Dialog policy determines the next-step actions for agents and hence is central to a dialogue system.

• However, when migrated to novel domains with little data, a policy model can fail to adapt due to insufficient interactions with the new environment.
• We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains, such as dialogue acts and slots.
• We decompose the state and action representation space into feature subspaces corresponding to these low-level components to facilitate cross-domain knowledge transfer.