Improving Search Efficiency in the Action Space of an Instance-Based Reinforcement Learning Technique for Multi-robot Systems.
Toshiyuki YasudaKazuhiro OhkuraPublished in: ECAL (2007)
Keyphrases
- search efficiency
- action space
- multi robot systems
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- multi robot
- multi agent
- autonomous robots
- reinforcement learning methods
- mobile robot
- state action
- continuous state spaces
- action selection
- reinforcement learning algorithms
- stochastic processes
- function approximation
- single agent
- multiple robots
- markov decision process
- function approximators
- optimal policy
- machine learning
- model free
- bayesian networks
- heuristic search