State Space Minimization Preserving Embeddings for Continuous-Time Markov Chains.
Susmoy DasArpit SharmaPublished in: EPEW (2021)
Keyphrases
- state space
- continuous time markov chains
- markov processes
- markov chain
- reinforcement learning
- poisson distribution
- markov decision processes
- dynamical systems
- numerically stable
- state variables
- dynamic programming
- markov process
- dimensionality reduction
- search space
- particle filter
- low dimensional
- objective function
- optimal policy
- initial state
- stochastic process