Combining Planning with Reinforcement Learning for Multi-robot Task Allocation.
Malcolm J. A. StrensNeil WindelinckxPublished in: Adaptive Agents and Multi-Agent Systems (2005)
Keyphrases
- reinforcement learning
- action selection
- multi robot task allocation
- planning problems
- function approximation
- markov decision processes
- state space
- partially observable
- machine learning
- model free
- decision theoretic
- multi robot systems
- temporal difference
- optimal policy
- learning algorithm
- complex domains
- multiple robots
- multi agent
- stochastic domains