A State Space Distribution Policy Based on Abstract Interpretation.
Simona OrzanJaco van de PolMiguel Valero EspadaPublished in: Electron. Notes Theor. Comput. Sci. (2005)
Keyphrases
- state space
- abstract interpretation
- optimal policy
- markov decision process
- termination analysis
- reinforcement learning
- static analysis
- heuristic search
- action space
- reward function
- active databases
- dynamic programming
- markov decision problems
- markov decision processes
- search space
- dynamic analysis
- continuous state spaces
- relational databases
- planning problems
- belief state
- reinforcement learning algorithms
- reasoning engine
- high level