Single-Agent vs. Multi-Agent Techniques for Concurrent Reinforcement Learning of Negotiation Dialogue Policies

40592

Knowledge Triples

Source Entity	Relationship	Target Entity
Multi-Agent Reinforcement Learning Method	comparesWith	Policy Hill Climbing Method
Multi-Agent Reinforcement Learning Method	comparesWith	Q-Learning Method
Multi-Agent Reinforcement Learning Method	usedFor	Dialogue Policies Task
Multi-Agent Reinforcement Learning Method	usedFor	Resource Allocation Negotiation Task
Single Agent Reinforcement Learning Method	usedFor	Dialogue Policies Task
Training Episodes Metric	affects	Dialogue Policies Task