Partially Observable Markov Decision Processes for Artificial Intelligence.
Leslie Pack KaelblingMichael L. LittmanAnthony R. CassandraPublished in: KI (1995)
Keyphrases
- partially observable markov decision processes
- artificial intelligence
- finite state
- planning under uncertainty
- optimal policy
- belief state
- reinforcement learning
- dynamical systems
- dynamic programming
- belief space
- decision problems
- continuous state
- stochastic domains
- partially observable stochastic games
- partial observability
- multi agent
- state space
- planning problems
- partially observable domains
- sequential decision making problems
- point based value iteration
- partially observable markov
- predictive state representations
- initial state
- partially observable
- infinite horizon
- approximate solutions
- data mining