Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition.
Ryuichi TakanobuRunze LiangMinlie HuangPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- multi agent
- learning systems
- partially observable environments
- supervised learning
- learning algorithm
- learning process
- prior knowledge
- multi agent systems
- multiagent systems
- learning tasks
- learning problems
- inverse reinforcement learning
- online learning
- knowledge acquisition
- mobile learning
- eligibility traces