Planning in stochastic domains for multiple agents with individual continuous resource state-spaces.
Emmanuel BenazeraPublished in: Auton. Agents Multi Agent Syst. (2011)
Keyphrases
- stochastic domains
- multiple agents
- state space
- planning problems
- multi agent
- action space
- single agent
- reward function
- multi agent coordination
- heuristic search
- reinforcement learning
- dynamic programming
- markov chain
- partially observable
- dynamical systems
- steady state
- partially observable markov decision processes
- search space
- markov decision problems
- decision making
- markov decision processes
- function approximation
- state variables
- mobile robot
- markov decision process