Randy Jia

Artificial Intelligence · 2022

A researcher in the Science corpus: 1 paper; trusts 12 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 17 citations into it; #8,511 of 35,345 by trust here, #21,878 by citations
• Management Science and Operations Research — 16 citations into it; #1,995 of 11,946 by trust here, #5,548 by citations
• Reinforcement Learning — 15 citations into it

Whom Randy Jia trusts overall

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

1. Ian Osband
2. Daniel Russo
3. Thomas Jaksch
4. Benjamin Van Roy
5. John Asmuth
6. Shipra Agrawal
7. Lihong Li
8. Peter L. Bartlett
9. Peter Auer
10. Michael L. Littman

Who trusts Randy Jia overall

1. Zihan Zhang
2. Lin F. Yang
3. Tor Lattimore
4. Chi Jin
5. Mengdi Wang
6. Xiangyang Ji
7. Csaba Szepesvari
8. Tonghan Wang
9. Alex Ayoub
10. Ronald Ortner

Papers from Randy Jia's perspective

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

1. ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES
2. Near-optimal Regret Bounds for Reinforcement Learning
3. Minimax Regret Bounds for Reinforcement Learning
4. (More) Efficient Reinforcement Learning via Posterior Sampling
5. Further Optimal Regret Bounds for Thompson Sampling
6. An Empirical Evaluation of Thompson Sampling
7. Reinforcement Learning: An Introduction
8. REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs
9. A Bayesian Sampling Approach to Exploration in Reinforcement Learning
10. Thompson Sampling for Contextual Bandits with Linear Payoffs

Their papers

• Optimistic posterior sampling for reinforcement learning: worst-case regret bounds (2022) — 240 citations