# Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing

arXiv: https://arxiv.org/abs/2311.14766 · HTML: https://mlsanity.com/paper/2311.14766/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 24 Nov 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 18 of 18)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO](https://mlsanity.com/paper/2005.12729/) (2020)
- [Offline A/B testing for Recommender Systems](https://mlsanity.com/paper/1801.07030/) (2018)
- [Better Rewards Yield Better Summaries: Learning to Summarise Without References](https://mlsanity.com/paper/1909.01214/) (2019)
- [Reward Uncertainty for Exploration in Preference-based Reinforcement Learning](https://mlsanity.com/paper/2205.12401/) (2022)
- [A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2101.01669/) (2021)
- [Learning Rewards from Linguistic Feedback](https://mlsanity.com/paper/2009.14715/) (2020)
- [Deep Learning for Click-Through Rate Estimation](https://mlsanity.com/paper/2104.10584/) (2021)
- [Customer Lifetime Value in Video Games Using Deep Learning and Parametric Models](https://mlsanity.com/paper/1811.12799/) (2018)

## Built on by (most cited first, 1 of 1)

- [Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse](https://mlsanity.com/paper/2403.09167/) (2024)

## Abstract (arXiv)

Reinforcement Learning from Human Feedback (RLHF) has played a crucial role in the success of large models such as ChatGPT. RLHF is a reinforcement learning framework which combines human feedback to improve learning effectiveness and performance. However, obtaining preferences feedback manually is quite expensive in commercial applications. Some statistical commercial indicators are usually more valuable and always ignored in RLHF. There exists a gap between commercial target and model training. In our research, we will attempt to fill this gap with statistical business feedback instead of human feedback, using AB testing which is a well-established statistical method. Reinforcement Learning from Statistical Feedback (RLSF) based on AB testing is proposed. Statistical inference methods are used to obtain preferences for training the reward network, which fine-tunes the pre-trained model in reinforcement learning framework, achieving greater business value. Furthermore, we extend AB testing with double selections at a single time-point to ANT testing with multiple selections at different feedback time points. Moreover, we design numerical experiences to validate the effectiveness of our algorithm framework.