A First-Order Approach to Accelerated Value Iteration.
Vineet GoyalJulien Grand-ClémentPublished in: Oper. Res. (2023)
Keyphrases
- markov decision processes
- state space
- higher order
- first order logic
- heuristic search
- optimal policy
- markov decision chains
- stochastic dominance
- belief space
- markov decision process
- dynamic programming
- reinforcement learning
- infinite horizon
- quantifier elimination
- stochastic shortest path
- decision diagrams
- database
- partially observable markov
- policy iteration
- partially observable markov decision processes
- horn clauses
- data model
- database systems
- case study
- information systems