Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these signals are only indirect proxies of user satisfaction and often suffer from noise and bias. Recently, explicit satisfaction feedback collected through questionnaires has emerged as a high-quality direct alignment supervision, but is extremely sparse and easily overwhelmed by abundant behavioral data, making it difficult to incorporate into online recommendation models. To address these challenges, we propose a novel framework which is towards End-to-End Alignment of user Satisfaction via Questionnaire, named EASQ, to enable real-time alignment of ranking models with true user satisfaction. Specifically, we first construct an independent parameter pathway for sparse questionnaire signals by combining a multi-task architecture and a lightweight LoRA module. The multi-task design separates sparse satisfaction supervision from dense behavioral signals, preventing the former from being overwhelmed. The LoRA module pre-inject these preferences in a parameter-isolated manner, ensuring stability in the backbone while optimizing user satisfaction. Furthermore, we employ a DPO-based optimization objective tailored for online learning, which aligns the main model outputs with sparse satisfaction signals in real time. This design enables end-to-end online learning, allowing the model to continuously adapt to new questionnaire feedback while maintaining the stability and effectiveness of the backbone. Extensive offline experiments and large-scale online A/B tests demonstrate that EASQ consistently improves user satisfaction metrics across multiple scenarios. EASQ has been successfully deployed in a production short-video recommendation system, delivering significant and stable business gains.

Abstract This paper introduces a novel approach called Chebyshev mapping and strongly connected topology for optimization of echo state network (ESN). To enhance the predictive performance of ESNs for time series data, Chebyshev mapping is employed to optimize the irregular input weight matrix. And the reservoir of the ESN is also replaced using an adjacency matrix derived from a digital chaotic system, resulting in a reservoir with strong connectivity properties. Numerical experiments are conducted on various time series datasets, including the Mackey–Glass time series, Lorenz time series and solar sunspot numbers, validating the effectiveness of the proposed optimization methods. Compared with the traditional ESNs, the optimization method proposed in this paper has higher predictive performance, and effectively reduce the reservoir’s size and model complexity.

Reinforcement learning is one of the most general paradigms to solve sequential decision making issues on the assumption that the action selection and environmental feedback are instantaneous, however, unfortunately this assumption is rarely true with regard to such ubiquitous delays in real-world system which could degrade the performance of reinforcement learning algorithms. The most common solution to solve a fixed delay problem is to design a forward dynamic model which is used to predict the newest state by recursively iterating over long steps so that a predicted state can be got and it would be taken as the agent's observation to make the newest decision. However, there exists cumulative errors during the iterative process which make long-term prediction inaccurate and further affect agent's decision. Motivated by the goal to reduce cumulative errors, we propose a new algorithm named Multi-step Prediction model with Delayed Observation(MPDO), aiming at accurately predicting future state at longer horizons for better decision making. Our approach includes two parts: a multi-step prediction model and a strategy training based on proximal policy optimization algorithms(PPO). Our model only needs a small amount of data to conduct dynamic modeling quickly, and the accuracy of prediction and iteration speed are higher than traditional methods. Experiments on Gym and MuJoCo show that MPDO achieves higher performance in such different tasks with different delays compared with other state-of-the-art methods, which verify our method's effectiveness.