Solving K-MDPs.
Jonathan Ferrer-MestresThomas G. DietterichOlivier BuffetIadine ChadèsPublished in: ICAPS (2020)
Keyphrases
- semi markov decision processes
- markov decision processes
- markov decision problems
- reinforcement learning
- algebraic decision diagrams
- sequential decision making problems
- state space
- factored mdps
- solving problems
- transition matrices
- optimal policy
- multi agent
- average reward
- neural network
- decision theoretic planning
- dynamic programming
- objective function
- stochastic shortest path
- machine learning