Autonomous blimp control using model-free reinforcement learning in a continuous state and action space.
Axel RottmannChristian PlagemannPeter HilgersWolfram BurgardPublished in: IROS (2007)
Keyphrases
- action space
- continuous state
- control policies
- state space
- reinforcement learning
- markov decision processes
- real valued
- action selection
- continuous state spaces
- control system
- robot navigation
- continuous action
- state action
- stochastic processes
- control problems
- finite state
- reinforcement learning methods
- cooperative
- single agent
- markov decision process
- state dependent
- function approximation
- planning problems
- optimal policy
- control strategies
- optimal control
- function approximators
- control policy
- decision problems
- markov chain