Performance Bounded Reinforcement Learning in Strategic Interactions.
Bikramjit BanerjeeJing PengPublished in: AAAI (2004)
Keyphrases
- reinforcement learning
- function approximation
- database
- learning algorithm
- reinforcement learning algorithms
- decision making
- multi agent
- temporal difference
- transfer learning
- case study
- learning process
- state space
- knowledge management
- genetic algorithm
- machine learning
- model free
- stochastic approximation
- interaction patterns
- capacity planning
- robotic control
- action selection
- markov decision processes
- dynamic programming
- hidden markov models
- decision trees
- real time