Contraction of the ITCPN State Space.
Hanifa BouchenebGérard BerthelotPublished in: Electron. Notes Theor. Comput. Sci. (2002)
Keyphrases
- state space
- dynamic programming
- reinforcement learning
- heuristic search
- state variables
- markov decision processes
- orders of magnitude
- markov chain
- belief change
- dynamical systems
- optimal policy
- action space
- state transition
- search space
- belief revision
- reinforcement learning algorithms
- markov decision process
- databases
- planning problems
- hidden markov models
- initial state
- goal state
- continuous state spaces
- continuous time markov process
- partially observable
- reward function
- artificial neural networks
- search algorithm
- similarity measure