# Collaborative Research: III: Small: Closing Sim-to-Real Gap in Reinforcement Learning via Randomization, Alignment, and Derivation

> **NSF 01002425DB NSF RESEARCH & RELATED ACTIVIT** · Clemson University (SC) · $290,739

## Abstract

Reinforcement Learning (RL) is a machine learning paradigm that strives to make optimal decision-making based on experience acting in an environment. In many cases, the "environment" refers to a simulator in the training stage and refers to the real world in the deployment stage. Training in the simulator brings a lot of advantages: lower cost, more safety, and more flexibility. However, it is almost impossible to design a perfect simulator that is identical to the real world. Thus, a decision-maker trained in the simulator may not function well in the real world. The discrepancy between the simulator and the real world is called the simulation-to-reality (sim-to-real) gap. This project will build new technologies to close the sim-to-real gap in both the training and the deployment stages. The research outcomes will benefit the development of next-generation RL techniques, which can improve the availability, applicability, and generalization of RL, and minimize the gap of RL between common practices and real-world practices. 

This project proposes to close the sim-to-real gap in reinforcement learning by three mechanisms: randomization, alignment, and derivation. Specifically, 1) the randomization mechanism generates a set of homogeneous simulators by original simulator parameter randomization. The simulator set will cover a wider range of state-action regions than the original simulator, have a larger overlap with the real-world environment, and thereafter result in a sma

## Key facts

- **NSF award ID:** 2550106
- **Awardee organization:** Clemson University (SC)
- **SAM.gov UEI:** H2BMNX7DSKU8
- **PI:** Kunpeng Liu
- **Primary program:** 01002425DB NSF RESEARCH & RELATED ACTIVIT
- **All programs:** SMALL PROJECT, INFO INTEGRATION & INFORMATICS
- **Estimated total:** $290,739
- **Funds obligated:** $290,739
- **Transaction type:** Standard Grant
- **Period:** 09/01/2025 → 08/31/2027

## Primary source

NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2550106

## Citation

> US National Science Foundation, Award 2550106, Collaborative Research: III: Small: Closing Sim-to-Real Gap in Reinforcement Learning via Randomization, Alignment, and Derivation. Retrieved via AI Analytics 2026-06-06 from https://api.ai-analytics.org/grant/nsf/2550106. Licensed CC0.

---

*[NSF Awards dataset](/datasets/nsf-awards) · CC0 1.0*