# PAC Reinforcement Learning without Real-World Feedback

arXiv: https://arxiv.org/abs/1909.10449 · HTML: https://mlsanity.com/paper/1909.10449/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Understanding Domain Randomization for Sim-to-real Transfer](https://mlsanity.com/paper/2110.03239/) (2021)
- [Provable Sim-to-real Transfer in Continuous Domain with Partial Observations](https://mlsanity.com/paper/2210.15598/) (2022)
- [Policy Gradient for LQR with Domain Randomization](https://mlsanity.com/paper/2503.24371/) (2025)
- [Statistical Guarantees for Offline Domain Randomization](https://mlsanity.com/paper/2506.10133/) (2025)
- [Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System](https://mlsanity.com/paper/2606.22145/) (2026)
- [Policy Gradient over History-Dependent Policy Classes for LQR with Domain Randomization](https://mlsanity.com/paper/2609.16300/) (2026)

## Abstract (arXiv)

This work studies reinforcement learning in the Sim-to-Real setting, in which an agent is first trained on a number of simulators before being deployed in the real world, with the aim of decreasing the real-world sample complexity requirement. Using a dynamic model known as a rich observation Markov decision process (ROMDP), we formulate a theoretical framework for Sim-to-Real in the situation where feedback in the real world is not available. We establish real-world sample complexity guarantees that are smaller than what is currently known for directly (i.e., without access to simulators) learning a ROMDP with feedback.