Keyphrases
- markov decision processes
- state space
- decision diagrams
- policy iteration
- optimal policy
- stochastic shortest path
- markov decision process
- reinforcement learning
- average reward
- finite state
- multi valued
- rewriting rules
- dynamic programming
- relational data
- database language
- modal logic
- partially observable
- average cost
- factored mdps
- decision theoretic planning
- query rewriting
- finite horizon
- relational databases
- infinite horizon
- conjunctive queries
- logic programming
- heuristic search
- data model
- planning under uncertainty
- database systems
- partially observable markov decision processes
- action space
- reward function
- fixed point
- least squares
- markov chain