Combining Learning Algorithms: An Approach to Markov Decision Processes.
Richardson RibeiroFábio FavarimMarco A. C. BarbosaAlessandro L. KoerichFabrício EnembreckPublished in: ICEIS (2012)
Keyphrases
- markov decision processes
- learning algorithm
- reinforcement learning algorithms
- reinforcement learning
- optimal policy
- finite state
- state space
- transition matrices
- dynamic programming
- policy iteration
- decision theoretic planning
- machine learning algorithms
- model based reinforcement learning
- factored mdps
- finite horizon
- partially observable
- reachability analysis
- risk sensitive
- machine learning
- decision processes
- planning under uncertainty
- policy evaluation
- learning problems
- average cost
- markov decision process
- learning rate
- infinite horizon
- reward function
- average reward
- real valued
- learning tasks
- stochastic shortest path
- multistage
- transfer learning
- action sets
- function approximation
- stationary policies
- action space