Keyphrases
- markov decision processes
- finite state
- reinforcement learning
- modal logic
- factored mdps
- optimal policy
- cellular automata
- state space
- finite automata
- finite horizon
- markov decision process
- dynamic programming
- average cost
- knowledge compilation
- policy iteration
- tree automata
- finite state machines
- semi markov decision processes
- lattice gas
- probabilistic automata
- decision diagrams
- average reward
- decision theoretic planning
- factored markov decision processes
- markov chain
- planning under uncertainty
- regular expressions
- reward function
- long run
- pattern matching
- markov decision problems
- model checking
- temporal logic
- partially observable
- infinite horizon
- model based reinforcement learning
- stochastic shortest path