Markov Chains and Markov Decision Processes in Isabelle/HOL.
Johannes HölzlPublished in: J. Autom. Reason. (2017)
Keyphrases
- markov decision processes
- markov chain
- theorem prover
- state space
- natural deduction
- finite state
- steady state
- inference rules
- reinforcement learning
- optimal policy
- theorem proving
- transition probabilities
- first order logic
- random walk
- dynamic programming
- markov model
- decision theoretic planning
- stochastic process
- monte carlo
- partially observable
- stationary distribution
- transition matrices
- finite horizon
- policy iteration
- markov processes
- action space
- infinite horizon
- average cost
- probabilistic automata
- markov decision process
- average reward
- sample path
- machine learning
- reward function