POMDP solving: what rewards do you really expect at execution?
Caroline Ponzoni Carvalho ChanelJean-Loup FargesFlorent Teichteil-KönigsbuchGuillaume InfantesPublished in: STAIRS (2010)
Keyphrases
- reinforcement learning
- markov decision processes
- sequential decision making problems
- markov decision problems
- reward function
- continuous state
- sequential decision making under uncertainty
- optimal policy
- multi agent
- combinatorial optimization
- finite state
- machine learning
- sufficient conditions
- partially observable markov decision process
- decision theoretic planning