Sanjiang Li

Reinforcement Learning · 2003

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 58 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 5 citations into it; #351 of 2,242 by trust here, #965 by citations

Whom Sanjiang Li trusts overall

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

1. Vijay R. Konda
2. Shun-ichi Amari
3. John N. Tsitsiklis

Who trusts Sanjiang Li overall

1. Sergey Levine
2. Jan Peters
3. Chelsea Finn
4. Vikash Kumar
5. Wen Sun
6. Pieter Abbeel
7. Herke Van Hoof
8. J. Bagnell
9. Gerhard Neumann
10. Philip S. Thomas

Papers from Sanjiang Li's perspective

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

1. Actor-Critic Algorithms
2. Methods of information geometry
3. Statistical Decision Rules and Optimal Inference
4. Autonomous helicopter control using reinforcement learning policy search methods
5. Policy Gradient Methods for Reinforcement Learning with Function Approximation
6. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
7. GENERATIVE ADVERSARIAL NETS
8. Reinforcement Learning: An Introduction
9. Learning internal representations by error propagation
10. Information Theory: 1948-1998 - Guest Editorial

Their papers

• Covariant policy search (2003) — 201 citations