A response-selection chatbot trained as an ensemble of 100 deep reinforcement learning agents, each on a cluster of dialogues, outperforms a single DRL agent and a Seq2Seq baseline on Persona-Chat.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ensemble-Based Deep Reinforcement Learning for Chatbots
A response-selection chatbot trained as an ensemble of 100 deep reinforcement learning agents, each on a cluster of dialogues, outperforms a single DRL agent and a Seq2Seq baseline on Persona-Chat.