# Predictive Preference Learning from Human Interventions

arXiv: https://arxiv.org/abs/2510.01545 · HTML: https://mlsanity.com/paper/2510.01545/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 51 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 30 of 33)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://mlsanity.com/paper/2401.08417/) (2024)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [Multimodal Motion Prediction with Stacked Transformers](https://mlsanity.com/paper/2103.11624/) (2021)
- [A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges](https://mlsanity.com/paper/2309.02473/) (2023)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [Human-in-the-Loop Imitation Learning using Remote Teleoperation](https://mlsanity.com/paper/2012.06733/) (2020)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1807.08364/) (2018)
- [Contrastive Preference Learning: Learning from Human Feedback without RL](https://mlsanity.com/paper/2310.13639/) (2023)
- [Shared Autonomy via Deep Reinforcement Learning](https://mlsanity.com/paper/1802.01744/) (2018)
- [Learning Reward Functions by Integrating Human Demonstrations and Preferences](https://mlsanity.com/paper/1906.08928/) (2019)
- [Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization](https://mlsanity.com/paper/2202.10341/) (2022)
- [Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation](https://mlsanity.com/paper/2006.14804/) (2020)
- [Multi-Task Interactive Robot Fleet Learning with Visual World Models](https://mlsanity.com/paper/2410.22689/) (2024)
- [Safe Driving via Expert Guided Policy Optimization](https://mlsanity.com/paper/2110.06831/) (2021)
- [Interactive Policy Learning through Confidence-Based Autonomy](https://mlsanity.com/paper/1401.3439/) (2014)

## Built on by (most cited first, 3 of 3)

- [Learning from Mistakes: Post-Training for Driving VLA with Takeover Data](https://mlsanity.com/paper/2603.14972/) (2026)
- [From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation](https://mlsanity.com/paper/2606.12603/) (2026)
- [Cue the Flow: Steering Flow-Matching Policies for Open-World Delivery Manipulation](https://mlsanity.com/paper/2609.38989/) (2026)

## Abstract (arXiv)

Learning from human involvement aims to incorporate the human subject to monitor and correct agent behavior errors. Although most interactive imitation learning methods focus on correcting the agent's action at the current state, they do not adjust its actions in future states, which may be potentially more hazardous. To address this, we introduce Predictive Preference Learning from Human Interventions (PPL), which leverages the implicit preference signals contained in human interventions to inform predictions of future rollouts. The key idea of PPL is to bootstrap each human intervention into L future time steps, called the preference horizon, with the assumption that the agent follows the same action and the human makes the same intervention in the preference horizon. By applying preference optimization on these future states, expert corrections are propagated into the safety-critical regions where the agent is expected to explore, significantly improving learning efficiency and reducing human demonstrations needed. We evaluate our approach with experiments on both autonomous driving and robotic manipulation benchmarks and demonstrate its efficiency and generality. Our theoretical analysis further shows that selecting an appropriate preference horizon L balances coverage of risky states with label correctness, thereby bounding the algorithmic optimality gap. Demo and code are available at: https://metadriverse.github.io/ppl