# Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models

arXiv: https://arxiv.org/abs/2608.08010 · HTML: https://mlsanity.com/paper/2608.08010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Toto: Time Series Optimized Transformer for Observability](https://mlsanity.com/paper/2407.07874/) (2024)
- [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2405.02358/) (2024)
- [Foundation Models for Time Series: A Survey](https://mlsanity.com/paper/2504.04011/) (2025)
- [Multi-Scale Finetuning for Encoder-based Time Series Foundation Models](https://mlsanity.com/paper/2506.14087/) (2025)
- [Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context](https://mlsanity.com/paper/2306.01112/) (2023)
- [ST-ExpertNet: A Deep Expert Framework for Traffic Prediction](https://mlsanity.com/paper/2205.07851/) (2022)
- [TimeHF: Billion-Scale Time Series Models Guided by Human Feedback](https://mlsanity.com/paper/2501.15942/) (2025)
- [Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective](https://mlsanity.com/paper/2509.22613/) (2025)
- [TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning](https://mlsanity.com/paper/2605.00015/) (2026)
- [S-GRPO: Unified Post-Training for Large Vision-Language Models](https://mlsanity.com/paper/2604.16557/) (2026)

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

- [Instance-Adaptive Prompts as Context for Time-Series Foundation Models](https://mlsanity.com/paper/2609.34786/) (2026)

## Abstract (arXiv)

Time series forecasting (TSF) plays an important role in a wide range of real-world applications. Recently, time series foundation models (TSFMs), pretrained on large-scale datasets, have demonstrated strong generalization capabilities and emerged as an important paradigm for TSF. Reinforcement learning (RL) post-training has consequently attracted growing attention as a means of further improving their performance on downstream tasks. However, we find that, in certain forecast regions, RL post-training may gradually shift the output distributions of TSFMs away from the ground truth, thereby limiting their performance. We refer to this phenomenon as suboptimal collapse. Our analysis suggests that difficulty in initially sampling high-quality trajectories near the ground truth is an important contributing factor to suboptimal collapse. To address this issue, we propose Ground-Truth Neighborhood Regularization (GTN-R) for RL post-training of TSFMs. GTN-R uses the ground truth as a reference for locating high-quality regions and guides the model's probability mass toward the ground-truth neighborhood. This increases the probability of sampling high-quality trajectories, mitigates suboptimal collapse, and improves performance. Moreover, GTN-R can be flexibly integrated into various RL methods for TSFMs. Extensive experiments show its effectiveness.