Rafail N. Gasimov
2001
A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 1 researcher here, as inferred from the citation graph.
Whom Rafail N. Gasimov trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Who trusts Rafail N. Gasimov overall
Papers from Rafail N. Gasimov's perspective
Ordered by how strongly the researchers Rafail N. Gasimov trusts endorse each paper. Same corpus, a different order for every researcher.
- On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
- Parallel and distributed computation
- Stable Function Approximation in Dynamic Programming
- Feature-based methods for large scale dynamic programming
- Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems
- Simulation-based optimization of Markov reward processes
- Dynamic Programming and Markov Processes
- Practical Issues in Temporal Difference Learning
- A Reinforcement Learning Method for Maximizing Undiscounted Rewards
- Learning from delayed rewards