On exploiting spectral properties for solving MDP with large state space.
Libin LiuArpan ChattopadhyayUrbashi MitraPublished in: Allerton (2017)
Keyphrases
- state space
- markov decision processes
- markov decision problems
- optimal policy
- reinforcement learning
- markov decision process
- dynamic programming
- markov chain
- heuristic search
- partially observable
- solving problems
- action space
- factored mdps
- finite state
- goal state
- reward function
- decision theoretic
- planning problems
- decision theoretic planning
- dynamic programming algorithms
- multispectral images
- spectral characteristics
- state and action spaces
- factored markov decision processes
- reinforcement learning algorithms
- belief state
- state variables
- dynamical systems
- multispectral
- multi agent