An exact iterative search algorithm for constrained Markov decision processes.
Hyeong Soo ChangPublished in: Autom. (2014)
Keyphrases
- markov decision processes
- search algorithm
- state space
- finite state
- optimal policy
- reinforcement learning
- policy iteration
- dynamic programming
- planning under uncertainty
- transition matrices
- decision theoretic planning
- search space
- decision processes
- factored mdps
- heuristic search
- infinite horizon
- reachability analysis
- reinforcement learning algorithms
- finite horizon
- action space
- risk sensitive
- average cost
- average reward
- partially observable
- stochastic shortest path
- model based reinforcement learning
- action sets
- state and action spaces
- markov decision process
- markov chain
- multi agent
- machine learning