Modelling and Controlling Uncertainty in Optimal Disassembly Planning through Reinforcement Learning.
Spyros A. ReveliotisPublished in: ICRA (2004)
Keyphrases
- reinforcement learning
- sequential decision problems
- partial observability
- dynamic programming
- partially observable
- incomplete knowledge
- action selection
- optimal control
- optimal solution
- heuristic search
- planning problems
- inventory routing
- machine learning
- function approximation
- uncertain data
- markov decision processes
- state space
- learning algorithm
- plan recognition
- expected utility
- ai planning
- blocks world
- optimal planning
- dynamical systems
- domain independent
- approximate dynamic programming
- external events