Efficiently Solving MDPs with Stochastic Mirror Descent.
Yujia JinAaron SidfordPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- semi markov decision processes
- reinforcement learning
- algebraic decision diagrams
- sequential decision making problems
- optimal policy
- factored mdps
- markov decision problems
- markov decision process
- monte carlo
- state space
- stochastic model
- decision theoretic planning
- finite horizon
- multistage
- linear programming
- transition matrices
- dynamic programming