Reinforcement learning with function approximation for cooperative navigation tasks.
Francisco S. MeloM. Isabel RibeiroPublished in: ICRA (2008)
Keyphrases
- function approximation
- navigation tasks
- reinforcement learning
- mobile robot
- path planning
- temporal difference
- temporal difference learning
- function approximators
- indoor environments
- multi agent
- model free
- temporal difference learning algorithms
- learning tasks
- multi agent systems
- reinforcement learning algorithms
- radial basis function
- state space
- machine learning
- markov decision processes
- neural network
- policy iteration
- action selection
- learning process
- exploration exploitation tradeoff