Improving the performance of complex agent plans through reinforcement learning.
Matteo LeonettiLuca IocchiPublished in: AAMAS (2010)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- plan execution
- intelligent agents
- autonomous agents
- multiagent systems
- learning agent
- multi agent systems
- machine learning
- function approximation
- partially observable
- rational agents
- high level
- markov decision process
- agent architecture
- agent model
- learning capabilities
- multiple agents
- learning algorithm
- autonomous learning
- belief desire intention
- reinforcement learning algorithms
- reward function
- pedagogical agents
- decision theoretic
- optimal control
- software agents
- dynamic environments
- state space
- mobile robot
- learning process
- cooperative