On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function.
Gellért WeiszPhilip AmortilaBarnabás JanzerYasin Abbasi-YadkoriNan JiangCsaba SzepesváriPublished in: CoRR (2021)
Keyphrases
- state space
- piecewise linear
- semi infinite programming
- database
- dynamic programming
- query processing
- markov decision processes
- linear space
- relevance feedback
- closed form
- optimal solution
- response time
- heuristic search
- initial state
- query evaluation
- planning problems
- stochastic domains
- information retrieval
- data sources
- data structure
- function approximation
- transition probabilities
- partially observable
- average cost
- range queries
- control policy
- optimal plans
- reinforcement learning