On the Undecidability of Probabilistic Planning and Infinite-Horizon Partially Observable Markov Decision Problems.
Omid MadaniSteve HanksAnne CondonPublished in: AAAI/IAAI (1999)
Keyphrases
- probabilistic planning
- partially observable
- infinite horizon
- markov decision problems
- optimal control
- markov decision processes
- long run
- optimal policy
- dynamic programming
- markov decision process
- state space
- lead time
- average cost
- decision problems
- dec pomdps
- average reward
- dynamical systems
- policy iteration
- special case
- computational complexity
- search algorithm