Bisimulation and Logical Preservation for Continuous-Time Markov Decision Processes.
Martin R. NeuhäußerJoost-Pieter KatoenPublished in: CONCUR (2007)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- policy iteration
- markov chain
- transition matrices
- dynamic programming
- reinforcement learning
- decision theoretic planning
- stationary policies
- reinforcement learning algorithms
- action space
- reachability analysis
- decision processes
- finite horizon
- heuristic search
- average reward
- average cost
- dynamical systems
- infinite horizon
- planning under uncertainty
- optimal control
- risk sensitive
- factored mdps
- optimal planning
- model based reinforcement learning
- partially observable
- reward function
- decision diagrams
- planning problems
- state and action spaces
- semi markov decision processes
- machine learning