The measure space structure of logical Markov decision processes.
Zhenzhen WangHancheng XingPublished in: FSKD (2013)
Keyphrases
- markov decision processes
- action space
- state space
- policy iteration
- dynamic programming
- finite state
- reinforcement learning
- optimal policy
- reachability analysis
- transition matrices
- factored mdps
- average reward
- reinforcement learning algorithms
- risk sensitive
- finite horizon
- learning algorithm
- model based reinforcement learning
- action sets
- decision processes
- average cost
- sufficient conditions
- planning under uncertainty
- decision theoretic planning
- state and action spaces
- partially observable
- reward function
- infinite horizon
- long run
- markov decision process
- search space