31 citations · 113 across the 23 of their papers we have counts for
24 papers
What Do Latent Action Models Actually Learn?
Chuheng Zhang, Tim Pearce, Pushi Zhang +5
Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames c…
Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction
Wei Shen, Xiaonan He, Chuheng Zhang +3
Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, thi…
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Yuliang Liu, Junjie Lu, Zhaoling Chen +10
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefin…
IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
Xiaoyu Chen, Junliang Guo, Tianyu He +5
We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically consistent action space across human and various robots. Through this unified latent action…
Policy Filtration for RLHF to Mitigate Noise in Reward Models
Chuheng Zhang, Wei Shen, Li Zhao +4
While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervi…
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
Yunseon Choi, Sangmin Bae, Seonghyun Ban +6
With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning reg…
Empowering Large Language Models on Robotic Manipulation with Affordance Prompting
Guangran Cheng, Chuheng Zhang, Wenzhe Cai +3
While large language models (LLMs) are successful in completing various language processing tasks, they easily fail to interact with the physical world by generating control sequen…
Pre-Trained Large Language Models for Industrial Control
Lei Song, Chuheng Zhang, Li Zhao +1
For industrial control, developing high-performance controllers with few samples and low technical debt is appealing. Foundation models, possessing rich prior knowledge obtained fr…
Towards Generalizable Reinforcement Learning for Trade Execution
Chuheng Zhang, Yitong Duan, Xiaoyu Chen +3
Optimized trade execution is to sell (or buy) a given amount of assets in a given time with the lowest possible trading cost. Recently, reinforcement learning (RL) has been applied…
A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management
Xianliang Yang, Zhihao Liu, Wei Jiang +4
Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios su…
RePreM: Representation Pre-training with Masked Model for Reinforcement Learning
Yuanying Cai, Chuheng Zhang, Wei Shen +3
Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Represent…
Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
Yuandong Ding, Mingxiao Feng, Guozi Liu +7
In this paper, we consider the inventory management (IM) problem where we need to make replenishment decisions for a large number of stock keeping units (SKUs) to balance their sup…
A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS
Wei Shen, Xiaonan He, Chuheng Zhang +2
Recently, spoken dialogue systems have been widely deployed in a variety of applications, serving a huge number of end-users. A common issue is that the errors resulting from noisy…
TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets
Yuanying Cai, Chuheng Zhang, Li Zhao +6
We consider an offline reinforcement learning (RL) setting where the agent need to learn from a dataset collected by rolling out multiple behavior policies. There are two challenge…
Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation
Ze Wang, Guogang Liao, Xiaowen Shi +6
Ads allocation, which involves allocating ads and organic items to limited slots in feed with the purpose of maximizing platform revenue, has become a research hotspot. Notice that…
Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks
Ze Wang, Guogang Liao, Xiaowen Shi +5
With the recent prevalence of reinforcement learning (RL), there have been tremendous interests in utilizing RL for ads allocation in recommendation platforms (e.g., e-commerce and…
Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation
Guogang Liao, Xiaowen Shi, Ze Wang +5
A mixed list of ads and organic items is usually displayed in feed and how to allocate the limited slots to maximize the overall revenue is a key problem. Meanwhile, modeling user…
Cross DQN: Cross Deep Q Network for Ads Allocation in Feed
Guogang Liao, Ze Wang, Xiaoxu Wu +5
E-commerce platforms usually display a mixed list of ads and organic items in feed. One key problem is to allocate the limited slots in the feed to maximize the overall revenue as…
Return-Based Contrastive Representation Learning for Reinforcement Learning
Guoqing Liu, Chuheng Zhang, Li Zhao +5
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxi…
DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis
Chuheng Zhang, Yuanqi Li, Xi Chen +3
Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superi…
Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcing
Wei Shen, Xiaonan He, Chuheng Zhang +3
In mobile crowdsourcing (MCS), the platform selects participants to complete location-aware tasks from the recruiters aiming to achieve multiple goals (e.g., profit maximization, e…
Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
Chuheng Zhang, Yuanying Cai, Longbo Huang +1
Exploration is essential for reinforcement learning (RL). To face the challenges of exploration, we consider a reward-free RL framework that completely separates exploration from e…
Policy Search by Target Distribution Learning for Continuous Control
Chuheng Zhang, Yuanqi Li, Jian Li
We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to dete…
Observation of topological links associated with Hopf insulators in a solid-state quantum simulator
X. -X. Yuan, L. He, S. -T. Wang +8
Hopf insulators are intriguing three-dimensional topological insulators characterized by an integer topological invariant. They originate from the mathematical theory of Hopf fibra…