Reinforcement Learning of Argumentation Dialogue Policies in Negotiation.
Kallirroi GeorgilaDavid R. TraumPublished in: INTERSPEECH (2011)
Keyphrases
- reinforcement learning
- optimal policy
- argumentation based negotiation
- multi agent
- dialogue games
- practical reasoning
- policy search
- resolve conflicts
- conflict resolution
- dispute resolution
- interaction protocols
- resolving conflicts
- markov decision process
- control policies
- reinforcement learning algorithms
- reward function
- markov decision processes
- function approximation
- reinforcement learning agents
- state space
- multi agent systems
- control policy
- cooperative
- discourse analysis
- socio cognitive
- human machine
- dialogue system
- software agents
- multiagent reinforcement learning
- mixed initiative
- learning capabilities
- partially observable markov decision processes
- model free
- policy gradient methods
- fitted q iteration
- access control policies
- markov decision problems
- learning algorithm
- automated negotiation
- agent communication
- electronic commerce
- legal reasoning
- negotiation support systems
- natural language
- agent societies
- dynamic programming
- decision problems
- infinite horizon
- temporal difference
- argumentation systems
- negotiation process
- cscl environments
- average reward
- long run
- computer mediated
- optimal control
- speech acts
- conceptual change
- decision making