Action Selection in Customer Value Optimization: An Approach Based on Covariate-Dependent Markov Decision Processes.
Angi RoeschHarald SchmidbauerPublished in: DMIN (2009)
Keyphrases
- markov decision processes
- action selection
- reinforcement learning
- action space
- total reward
- state space
- optimal policy
- policy iteration
- finite state
- basal ganglia
- robot soccer
- transition matrices
- temporal difference
- reinforcement learning algorithms
- dynamic programming
- decision making
- average reward
- decision theoretic planning
- finite horizon
- average cost
- planning under uncertainty
- markov decision process
- partially observable
- infinite horizon
- reward function
- factored mdps
- state and action spaces
- control policies
- model based reinforcement learning
- action sets
- reachability analysis
- real time dynamic programming
- machine learning
- semi markov decision processes
- multi agent
- markov chain
- function approximation
- optimal control
- model free