Reduction of temporal complexity in Markov decision processes.
Ma. de Guadalupe García-HernándezJosé Ruiz-PinalesSergio E. Ledesma-OrozcoJuan Gabriel Aviña-CervantesPublished in: CONIELECOMP (2012)
Keyphrases
- markov decision processes
- finite state
- reinforcement learning
- optimal policy
- transition matrices
- state space
- dynamic programming
- reachability analysis
- decision theoretic planning
- risk sensitive
- policy iteration
- decision diagrams
- average cost
- factored mdps
- reinforcement learning algorithms
- infinite horizon
- decision processes
- average reward
- finite horizon
- partially observable
- decision problems
- planning under uncertainty
- markov decision process
- model based reinforcement learning
- action space
- action sets
- model checking
- stochastic shortest path