Dharmashankar Subramanian

Reinforcement Learning · 2014

A researcher in the Science corpus: 1 paper; trusts 11 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 7 citations into it

Whom Dharmashankar Subramanian trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey J. Gordon
2. Garud N. Iyengar
3. John N. Tsitsiklis
4. Wolfram Wiesemann
5. Thomas Dueholm Hansen
6. Benjamin Van Roy

Who trusts Dharmashankar Subramanian overall

1. Yinlam Chow

Papers from Dharmashankar Subramanian's perspective

Ordered by how strongly the researchers Dharmashankar Subramanian trusts endorse each paper. Same corpus, a different order for every researcher.

1. Robust Dynamic Programming
2. Stable Function Approximation in Dynamic Programming
3. Robust Control of Markov Decision Processes with Uncertain Transition Matrices
4. Least-Squares Policy Iteration
5. An Analysis of Temporal-Difference Learning with Function Approximation
6. Foundations of Stochastic Inventory Theory
7. Strategy Iteration Is Strongly Polynomial for 2-Player Turn-Based Stochastic Games with a Constant Discount Factor
8. Robust Markov Decision Processes
9. Markov Decision Processes: Discrete Stochastic Dynamic Programming
10. ImageNet classification with deep convolutional neural networks

Their papers

• RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning (2014) — 41 citations