Using Normative Markov Decision Processes for evaluating electronic contracts.
Moser Silva FagundesSascha OssowskiMichael LuckSimon MilesPublished in: AI Commun. (2012)
Keyphrases
- markov decision processes
- finite state
- optimal policy
- policy iteration
- state space
- dynamic programming
- reinforcement learning
- transition matrices
- infinite horizon
- partially observable
- planning under uncertainty
- supply chain
- decision theoretic planning
- action sets
- reachability analysis
- decision processes
- finite horizon
- action space
- reinforcement learning algorithms
- average reward
- model based reinforcement learning
- semi markov decision processes
- factored mdps
- average cost
- multi agent systems
- state and action spaces
- risk sensitive
- state abstraction
- continuous state spaces
- interval estimation