Aarti Singh

Artificial Intelligence · with Dubrawski · 2020

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 17 citations into it
• Reinforcement Learning — 15 citations into it
• Management Science and Operations Research — 12 citations into it

Whom Aarti Singh trusts overall

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

1. Yisong Yue
2. Chi Jin

Papers from Aarti Singh's perspective

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

1. Deep Reinforcement Learning from Human Preferences (Neural Information Processing Systems)
2. Concrete Problems in AI Safety
3. The K-armed Dueling Bandits Problem
4. Is Q-learning Provably Efficient?
5. Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
6. On the Sample Complexity of Reinforcement Learning with a Generative Model
7. Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning
8. Policy Search by Dynamic Programming
9. Provably efficient RL with Rich Observations via Latent State Decoding
10. Beat the Mean Bandit

Their papers

• Preference-based Reinforcement Learning with Finite-Time Guarantees (2020) — 81 citations