Eliciting Additive Reward Functions for Markov Decision Processes.
Kevin ReganCraig BoutilierPublished in: IJCAI (2011)
Keyphrases
- markov decision processes
- reward function
- optimal policy
- reinforcement learning algorithms
- state space
- reinforcement learning
- partially observable
- finite state
- transition matrices
- policy iteration
- markov decision process
- dynamic programming
- multi attribute
- factored mdps
- decision processes
- planning under uncertainty
- infinite horizon
- decision theoretic planning
- hierarchical reinforcement learning
- average cost
- finite horizon
- action space
- average reward
- monte carlo
- stochastic games
- markov decision problems
- learning algorithm