Point-Based Value Iteration for Finite-Horizon POMDPs.
Erwin WalravenMatthijs T. J. SpaanPublished in: J. Artif. Intell. Res. (2019)
Keyphrases
- point based value iteration
- finite horizon
- optimal policy
- partially observable markov decision processes
- infinite horizon
- markov decision processes
- belief state
- control policies
- continuous state
- belief space
- multistage
- state space
- markov decision process
- planning under uncertainty
- average cost
- finite state
- partially observable
- long run
- optimal control
- decision problems
- non stationary
- reinforcement learning
- state dependent
- dynamic programming
- initial state
- machine learning
- sufficient conditions