Stochastic Transition Model for Discrete Agent Movements.
Michael SchultzHartmut FrickePublished in: ACRI (2010)
Keyphrases
- transition model
- state transition
- reward function
- reinforcement learning
- multi agent systems
- multi agent
- finite number
- state transitions
- decision making
- multiple agents
- learning capabilities
- markov decision problems
- decision theoretic
- monte carlo
- dynamic environments
- input output
- neural network
- computational complexity