The Branching Time Spectrum for Continuous-time MDPs
Lei SongLijun ZhangJens Chr. GodskesenPublished in: CoRR (2012)
Keyphrases
- markov decision processes
- state space
- reinforcement learning
- markov chain
- dynamical systems
- markov processes
- finite horizon
- finite state
- optimal control
- model checking
- temporal reasoning
- factored mdps
- markov decision problems
- temporal logic
- partially observable
- dynamic programming
- factored markov decision processes
- continuous time bayesian networks
- semi markov decision processes
- stationary policies
- planning under uncertainty
- optimal policy
- markov decision process
- iterative learning control
- dec pomdps
- infinite horizon
- learning algorithm
- stochastic processes
- policy iteration
- probabilistic planning
- linear programming
- action space
- decision theoretic planning
- video sequences
- stochastic domains
- transition probabilities
- real time dynamic programming
- decision theoretic
- heuristic search