Introducing Deep Reinforcement Learning to Nlu Ranking Tasks.
Ge YuEmre BarutChengwei SuPublished in: ICASSP (2021)
Keyphrases
- reinforcement learning
- transfer learning
- multi agent
- function approximation
- learning process
- dynamic programming
- genetic algorithm
- multi agent environments
- link analysis
- learning algorithm
- ranked list
- learning classifier systems
- model free
- temporal difference
- reinforcement learning algorithms
- real robot
- markov decision process
- multiple tasks
- information retrieval
- transferring knowledge