Get started
Author

Harsh Satija

A Survey of Exploration Methods in Reinforcement Learning
2021 · Amin, Susan, Gomrokchi, Maziar, et al. · arXiv (Cornell University) · 126
PDF
Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate
2025 · Wynn, Andrea, Satija, Harsh, et al. · arXiv (Cornell University) · 96
PDF
Decoupling Dynamics and Reward for Transfer Learning
2018 · Zhang, Amy, Satija, Harsh, et al. · arXiv (Cornell University) · 72
PDF
Constrained Markov Decision Processes via Backward Value Functions
2020 · Satija, Harsh, Amortila, Philip, et al. · arXiv (Cornell University) · 30
PDF
Randomized Value Functions via Multiplicative Normalizing Flows
2018 · Touati, Ahmed, Satija, Harsh, et al. · arXiv (Cornell University) · 23
PDF
Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards
2020 · Amin, Susan, Gomrokchi, Maziar, et al. · arXiv (Cornell University) · 14
PDF
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs
2021 · Satija, Harsh, Thomas, Philip S., et al. · arXiv (Cornell University) · 8
PDF
Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs
2026 · Wynn, Andrea, Satija, Harsh, et al. · arXiv (Cornell University)
PDF
Works count: 10
Citation count: 369
H-index: 7
I10-index: 6
Year
Topic
Type