Mobile Robotics Planning Using Abstract Markov Decision Processes.
Pierre LarocheFrançois CharpilletRené SchottPublished in: ICTAI (1999)
Keyphrases
- markov decision processes
- mobile robotics
- macro actions
- planning under uncertainty
- mobile robot
- partially observable
- decision theoretic planning
- state space
- optimal policy
- finite state
- reinforcement learning
- dynamic programming
- object recognition
- policy iteration
- reachability analysis
- planning problems
- probabilistic planning
- model based reinforcement learning
- transition matrices
- infinite horizon
- decision processes
- partially observable markov decision processes
- markov decision process
- average cost
- ai planning
- action space
- average reward
- reinforcement learning algorithms
- factored mdps
- heuristic search
- finite horizon
- risk sensitive
- semi markov decision processes
- computer vision
- markov chain
- discounted reward
- domain independent
- state and action spaces
- function approximation
- learning algorithm