Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes.
Nicholay TopinNicholas HaltmeyerShawn SquireJohn WinderMarie desJardinsJames MacGlashanPublished in: IJCAI (2015)
Keyphrases
- markov decision processes
- object oriented
- learning transfer
- finite state
- optimal policy
- state space
- reinforcement learning
- policy iteration
- decision theoretic planning
- reachability analysis
- transition matrices
- partially observable
- dynamic programming
- infinite horizon
- relational databases
- finite horizon
- data mining
- human resources
- model based reinforcement learning
- planning under uncertainty
- average cost
- action space
- action sets
- markov decision process
- average reward
- declarative knowledge
- business processes
- domain knowledge
- reward function