# Learning Calibratable Policies using Programmatic Style-Consistency

arXiv: https://arxiv.org/abs/1910.01179 · HTML: https://mlsanity.com/paper/1910.01179/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 11 of 11)

- [The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions](https://mlsanity.com/paper/2104.02710/) (2021)
- [UniMASK: Unified Inference in Sequential Decision Problems](https://mlsanity.com/paper/2211.10869/) (2022)
- [Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports](https://mlsanity.com/paper/2405.17680/) (2024)
- [baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling](https://mlsanity.com/paper/2102.03291/) (2021)
- [MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior](https://mlsanity.com/paper/2207.10553/) (2022)
- [Unsupervised Learning of Neurosymbolic Encoders](https://mlsanity.com/paper/2107.13132/) (2021)
- [Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers](https://mlsanity.com/paper/2204.13326/) (2022)
- [Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining](https://mlsanity.com/paper/2507.09513/) (2025)
- [Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning](https://mlsanity.com/paper/2410.15910/) (2024)
- [Learning a Hierarchical Planner from Humans in Multiple Generations](https://mlsanity.com/paper/2310.11614/) (2023)
- [Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment](https://mlsanity.com/paper/2601.22823/) (2026)

## Abstract (arXiv)

We study the problem of controllable generation of long-term sequential behaviors, where the goal is to calibrate to multiple behavior styles simultaneously. In contrast to the well-studied areas of controllable generation of images, text, and speech, there are two questions that pose significant challenges when generating long-term behaviors: how should we specify the factors of variation to control, and how can we ensure that the generated behavior faithfully demonstrates combinatorially many styles? We leverage programmatic labeling functions to specify controllable styles, and derive a formal notion of style-consistency as a learning objective, which can then be solved using conventional policy learning approaches. We evaluate our framework using demonstrations from professional basketball players and agents in the MuJoCo physics environment, and show that existing approaches that do not explicitly enforce style-consistency fail to generate diverse behaviors whereas our learned policies can be calibrated for up to 1024 distinct style combinations.