Strict-sense constrained Markov decision processes.
Shun-Pin HsuAristotle ArapostathisPublished in: SMC (1) (2004)
Keyphrases
- markov decision processes
- state space
- finite state
- policy iteration
- decision theoretic planning
- reachability analysis
- dynamic programming
- transition matrices
- optimal policy
- reinforcement learning
- average reward
- reinforcement learning algorithms
- markov decision process
- factored mdps
- average cost
- state and action spaces
- finite horizon
- decision processes
- partially observable
- infinite horizon
- risk sensitive
- planning under uncertainty
- action space
- reward function
- action sets
- model based reinforcement learning
- partially observable markov decision processes
- supply chain
- decision making
- stochastic shortest path