# Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition

arXiv: https://arxiv.org/abs/2603.16043 · HTML: https://mlsanity.com/paper/2603.16043/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 24 of its 51 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Learning explanations that are hard to vary](https://mlsanity.com/paper/2009.00329/) (2020)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Improving Position Encoding of Transformers for Multivariate Time Series Classification](https://mlsanity.com/paper/2305.16642/) (2023)
- [UniMTS: Unified Pre-training for Motion Time Series](https://mlsanity.com/paper/2410.19818/) (2024)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2402.01049/) (2024)
- [SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition](https://mlsanity.com/paper/2212.00724/) (2022)
- [Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition](https://mlsanity.com/paper/2310.18562/) (2023)
- [Domain Generalization for Activity Recognition via Adaptive Feature Fusion](https://mlsanity.com/paper/2207.11221/) (2022)
- [Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition](https://mlsanity.com/paper/2209.11750/) (2022)
- [Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning](https://mlsanity.com/paper/2306.04641/) (2023)
- [TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation](https://mlsanity.com/paper/2209.09092/) (2022)
- [Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition](https://mlsanity.com/paper/2406.04609/) (2024)
- [Generalizable Sensor-Based Activity Recognition via Categorical Concept Invariant Learning](https://mlsanity.com/paper/2412.13594/) (2024)
- [Deconfounding Causal Inference through Two-Branch Framework with Early-Forking for Sensor-Based Cross-Domain Activity Recognition](https://mlsanity.com/paper/2507.03898/) (2025)

## Abstract (arXiv)

Human Activity Recognition using wearable inertial sensors is foundational to healthcare monitoring, fitness analytics, and context-aware computing, yet its deployment is hindered by cross-user variability arising from heterogeneous physiological traits, motor habits, and sensor placements. Existing domain generalization approaches either neglect temporal dependencies in sensor streams or depend on impractical target-domain annotations. We propose a different paradigm: modeling generalizable feature extraction as a collaborative sequential generation process governed by reinforcement learning. Our framework, CTFG (Collaborative Temporal Feature Generation), employs a Transformer-based autoregressive generator that incrementally constructs feature token sequences, each conditioned on prior context and the encoded sensor input. The generator is optimized via Group-Relative Policy Optimization, a critic-free algorithm that evaluates each generated sequence against a cohort of alternatives sampled from the same input, deriving advantages through intra-group normalization rather than learned value estimation. This design eliminates the distribution-dependent bias inherent in critic-based methods and provides self-calibrating optimization signals that remain stable across heterogeneous user distributions. A tri-objective reward comprising class discrimination, cross-user invariance, and temporal fidelity jointly shapes the feature space to separate activities, align user distributions, and preserve fine-grained temporal content. Evaluations on the DSADS and PAMAP2 benchmarks demonstrate state-of-the-art cross-user accuracy (88.53% and 75.22%), substantial reduction in inter-task training variance, accelerated convergence, and robust generalization under varying action-space dimensionalities.