Author name cluster

Pengjie Gu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

12 papers

2 author rows

ICML Conference 2025 Conference Paper

Cradle: Empowering Foundation Agents towards General Computer Control

Weihao Tan
Wentao Zhang 0007
Xinrun Xu
Haochong Xia
Ziluo Ding
Boyu Li 0003
Bohan Zhou
Junpeng Yue

Despite their success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i. e. , using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Information Gathering, Self-Reflection, Task Inference, Skill Curation, Action Planning, and Memory, Cradle is able to understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning and information retrieval, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games (Red Dead Redemption 2, Cities: Skylines, Stardew Valley and Dealer’s Life 2), five software applications (Chrome, Outlook, Feishu, Meitu and CapCut), and a comprehensive benchmark, OSWorld. With a unified interface to interact with any software, Cradle greatly extends the reach of foundation agents thus paving the way for generalist agents.

Details

ECAI Conference 2025 Conference Paper

DiTAC: Discrete Teamwork Abstraction for Ad Hoc Collaboration

Jing Wang 0055
Pengjie Gu
Mengchen Zhao
Guangyong Chen
Furui Liu
Pheng-Ann Heng

Training autonomous agents to collaborate with unknown teammates in cooperative multi-agent environments remains a fundamental challenge in ad hoc teamwork research. Conventional approaches rely heavily on online interactions with arbitrary teammates under the assumption of full observability. However, in real-world scenarios, teammate policies are often inaccessible, making historical trajectory rollouts a more practical alternative. We propose DiTAC, a method that learns discrete teamwork abstractions for ad hoc collaboration by automatically extracting latent cooperation patterns from short trajectory segments and adapting effectively to diverse teammate behaviors. To mitigate the out-of-distribution challenge, we constrain learned representations within a discrete code-book. Furthermore, we employ a masked bidirectional transformer architecture to infer teammate behaviors from local observations, thereby relaxing the full observability assumption. Empirical results demonstrate that DiTAC significantly outperforms existing baselines and its variants across widely-used ad hoc teamwork tasks.

Details

NeurIPS Conference 2025 Conference Paper

Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning

Yiwen Zhu
Jinyi Liu
Pengjie Gu
Yifu Yuan
Zhenxing Ge
Wenya Wei
Zhou Fang
Yujing Hu

Reinforcement learning (RL) heavily depends on well-designed reward functions, which are often biased and difficult to design for complex behaviors. Preference-based RL (PbRL) addresses this by learning reward models from human feedback, but its practicality is constrained by a critical dilemma: while existing methods reduce human effort through query optimization, they neglect the preference buffer's restricted coverage — a factor that fundamentally determines the reliability of reward model. We systematically demonstrate this limitation creates distributional mismatch: reward models trained on static buffers reliably assess in-distribution trajectories but falter with out-of-distribution (OOD) trajectories from policy exploration. Crucially, such failures in policy-proximal regions directly misguide iterative policy updates. To address this, we propose Proximal Policy Exploration (PPE) with two key components: (1) a proximal-policy extension method that expands exploration in undersampled policy-proximal regions, and (2) a mixture distribution query method that balances in-distribution and OOD trajectory sampling. By enhancing buffer coverage while preserving evaluation accuracy in policy-proximal regions, PPE enables more reliable policy updates. Experiments across continuous control tasks demonstrate that PPE enhances preference feedback utilization efficiency and RL sample efficiency over baselines, highlighting preference buffer coverage management's vital role in PbRL.

PDF Details

NeurIPS Conference 2025 Conference Paper

MTRec: Learning to Align with User Preferences via Mental Reward Models

Mengchen Zhao
Yifan Gao
Yaqing Hou
Xiangyang Li
Pengjie Gu
Zhenhua Dong
Ruiming Tang
Yi Cai

Recommendation models are predominantly trained using implicit user feedback, since explicit feedback is often costly to obtain. However, implicit feedback, such as clicks, does not always reflect users' real preferences. For example, a user might click on a news article because of its attractive headline, but end up feeling uncomfortable after reading the content. In the absence of explicit feedback, such erroneous implicit signals may severely mislead recommender systems. In this paper, we propose MTRec, a novel sequential recommendation framework designed to align with real user preferences by uncovering their internal satisfaction on recommended items. Specifically, we introduce a mental reward model to quantify user satisfaction and propose a distributional inverse reinforcement learning approach to learn it. The learned mental reward model is then used to guide recommendation models to better align with users’ real preferences. Our experiments show that MTRec brings significant improvements to a variety of recommendation models. We also deploy MTRec on an industrial short video platform and observe a 7\% increase in average user viewing time.

PDF Details

IJCAI Conference 2024 Conference Paper

PoRank: A Practical Framework for Learning to Rank Policies

Pengjie Gu
Mengchen Zhao
Xu He
Yi Cai
Bo An

In many real-world scenarios, we need to select from a set of candidate policies before online deployment. Although existing Off-policy evaluation (OPE) methods can be used to estimate the online performance, they suffer from high variance. Fortunately, we care only about the ranking of the candidate policies, rather than their exact online rewards. Based on this, we propose a novel framework PoRank for learning to rank policies. In practice, learning to rank policies faces two main challenges: 1) generalization over the huge policy space and 2) lack of supervision signals. To overcome the first challenge, PoRank uses a Policy Comparison Transformer (PCT) for learning cross-policy representations, which capture the core discrepancies between policies and generalizes well across the whole policy space. The second challenge arises because learning to rank requires online comparisons of policies as ground-truth labels, whereas deploying policies online might be highly expensive. To overcome this, PoRank adopts a crowdsourcing based learning-to-rank (LTR) framework, where a set of OPE algorithms are employed to provide weak comparison labels. Experimental results show that PoRank not only outperforms baselines when the ground-truth labels are provided, but also achieves competitive performance when the ground-truth labels are unavailable.

PDF Details DOI

ICML Conference 2024 Conference Paper

Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree

Lang Feng 0002
Pengjie Gu
Bo An 0001
Gang Pan 0001

Diffusion planners have shown promise in handling long-horizon and sparse-reward tasks due to the non-autoregressive plan generation. However, their inherent stochastic risk of generating infeasible trajectories presents significant challenges to their reliability and stability. We introduce a novel approach, the Trajectory Aggregation Tree (TAT), to address this issue in diffusion planners. Compared to prior methods that rely solely on raw trajectory predictions, TAT aggregates information from both historical and current trajectories, forming a dynamic tree-like structure. Each trajectory is conceptualized as a branch and individual states as nodes. As the structure evolves with the integration of new trajectories, unreliable states are marginalized, and the most impactful nodes are prioritized for decision-making. TAT can be deployed without modifying the original training and sampling pipelines of diffusion planners, making it a training-free, ready-to-deploy solution. We provide both theoretical analysis and empirical evidence to support TAT’s effectiveness. Our results highlight its remarkable ability to resist the risk from unreliable trajectories, guarantee the performance boosting of diffusion planners in 100% of tasks, and exhibit an appreciable tolerance margin for sample quality, thereby enabling planning with a more than $3\times$ acceleration.

Details

ICLR Conference 2024 Conference Paper

Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution

Shanqi Liu
Dong Xing
Pengjie Gu
Xinrun Wang
Bo An 0001
Yong Liu

Cooperative multi-agent reinforcement learning (MARL) is extensively used for solving complex cooperative tasks, and value decomposition methods are a prevalent approach for this domain. However, these methods have not been successful in addressing both homogeneous and heterogeneous tasks simultaneously which is a crucial aspect for the practical application of cooperative agents. On one hand, value decomposition methods demonstrate superior performance in homogeneous tasks. Nevertheless, they tend to produce agents with similar policies, which is unsuitable for heterogeneous tasks. On the other hand, solutions based on personalized observation or assigned roles are well-suited for heterogeneous tasks. However, they often lead to a trade-off situation where the agent's performance in homogeneous scenarios is negatively affected due to the aggregation of distinct policies. An alternative approach is to adopt sequential execution policies, which offer a flexible form for learning both types of tasks. However, learning sequential execution policies poses challenges in terms of credit assignment, and the limited information about subsequently executed agents can lead to sub-optimal solutions, which is known as the relative over-generalization problem. To tackle these issues, this paper proposes Greedy Sequential Execution (GSE) as a solution to learn the optimal policy that covers both scenarios. In the proposed GSE framework, we introduce an individual utility function into the framework of value decomposition to consider the complex interactions between agents. This function is capable of representing both the homogeneous and heterogeneous optimal policies. Furthermore, we utilize greedy marginal contribution calculated by the utility function as the credit value of the sequential execution policy to address the credit assignment and relative over-generalization problem. We evaluated GSE in both homogeneous and heterogeneous scenarios. The results demonstrate that GSE achieves significant improvement in performance across multiple domains, especially in scenarios involving both homogeneous and heterogeneous tasks.

Details

ICML Conference 2023 Conference Paper

Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification

Dong Xing
Pengjie Gu
Qian Zheng
Xinrun Wang
Shanqi Liu
Longtao Zheng
Bo An 0001
Gang Pan 0001

Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation of types and then pre-train the best response for each type. However, most of them do not consider the distribution of teammate instances within a type. This could expose the agent to the hidden risk of type confounding. In the worst case, the best response for an abstract teammate type could be the worst response for all specific instances of that type. This work addresses the issue from the lens of causal inference. We first theoretically demonstrate that this phenomenon is due to the spurious correlation brought by uncontrolled teammate distribution. Then, we propose our solution, CTCAT, which disentangles such correlation through an instance-wise teammate feedback rectification. This operation reweights the interaction of teammate instances within a shared type to reduce the influence of type confounding. The effect of CTCAT is evaluated in multiple domains, including classic ad hoc teamwork tasks and real-world scenarios. Results show that CTCAT is robust to the influence of type confounding, a practical issue that directly hazards the robustness of our trained agents but was unnoticed in previous works.

Details

NeurIPS Conference 2023 Conference Paper

Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

Pengjie Gu
Xinyu Cai
Dong Xing
Xinrun Wang
Mengchen Zhao
Bo An

Offline Reinforcement Learning (RL) has demonstrated promising results in various applications by learning policies from previously collected datasets, reducing the need for online exploration and interactions. However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the masked observations during execution, and ii) the information of which parts of observations are masked is usually unknown during training. In order to address these challenges, we present Offline RL with DiscrEte pRoxy representations (ORDER), a probabilistic framework which leverages novel state representations to improve the robustness against diverse masked observabilities. Specifically, we propose a discrete representation of the states and use a proxy representation to recover the states from masked partial observable trajectories. The training of ORDER can be compactly described as the following three steps. i) Learning the discrete state representations on data with full observations, ii) Training the decision module based on the discrete representations, and iii) Training the proxy discrete representations on the data with various partial observations, aligning with the discrete representations. We conduct extensive experiments to evaluate ORDER, showcasing its effectiveness in offline RL for diverse partially observable scenarios and highlighting the significance of discrete proxy representations in generalization performance. ORDER is a flexible framework to employ any offline RL algorithms and we hope that ORDER can pave the way for the deployment of RL policy against various partial observabilities in the real world.

PDF Details

ICML Conference 2022 Conference Paper

Learning Pseudometric-based Action Representations for Offline Reinforcement Learning

Pengjie Gu
Mengchen Zhao
Chen Chen 0077
Dong Li 0016
Jianye Hao
Bo An 0001

Offline reinforcement learning is a promising approach for practical applications since it does not require interactions with real-world environments. However, existing offline RL methods only work well in environments with continuous or small discrete action spaces. In environments with large and discrete action spaces, such as recommender systems and dialogue systems, the performance of existing methods decreases drastically because they suffer from inaccurate value estimation for a large proportion of out-of-distribution (o. o. d.) actions. While recent works have demonstrated that online RL benefits from incorporating semantic information in action representations, unfortunately, they fail to learn reasonable relative distances between action representations, which is key to offline RL to reduce the influence of o. o. d. actions. This paper proposes an action representation learning framework for offline RL based on a pseudometric, which measures both the behavioral relation and the data-distributional relation between actions. We provide theoretical analysis on the continuity of the expected Q-values and the offline policy improvement using the learned action representations. Experimental results show that our methods significantly improve the performance of two typical offline RL methods in environments with large and discrete action spaces.

Details

ICLR Conference 2022 Conference Paper

Online Ad Hoc Teamwork under Partial Observability

Pengjie Gu
Mengchen Zhao
Jianye Hao
Bo An 0001

Autonomous agents often need to work together as a team to accomplish complex cooperative tasks. Due to privacy and other realistic constraints, agents might need to collaborate with previously unknown teammates on the fly. This problem is known as ad hoc teamwork, which remains a core research challenge. Prior works usually rely heavily on strong assumptions like full observability, fixed and predefined teammates' types. This paper relaxes these assumptions with a novel reinforcement learning framework called ODITS, which allows the autonomous agent to adapt to arbitrary teammates in an online fashion. Instead of limiting teammates into a finite set of predefined types, ODITS automatically learns latent variables of teammates' behaviors to infer how to cooperate with new teammates effectively. To overcome partial observability, we introduce an information-based regularizer to derive proxy representations of the learned variables from local observations. Extensive experimental results show that ODITS significantly outperforms various baselines in widely used ad hoc teamwork tasks.

Details

IJCAI Conference 2019 Conference Paper

STCA: Spatio-Temporal Credit Assignment with Delayed Feedback in Deep Spiking Neural Networks

Pengjie Gu
Rong Xiao
Gang Pan
Huajin Tang

The temporal credit assignment problem, which aims to discover the predictive features hidden in distracting background streams with delayed feedback, remains a core challenge in biological and machine learning. To address this issue, we propose a novel spatio-temporal credit assignment algorithm called STCA for training deep spiking neural networks (DSNNs). We present a new spatiotemporal error backpropagation policy by defining a temporal based loss function, which is able to credit the network losses to spatial and temporal domains simultaneously. Experimental results on MNIST dataset and a music dataset (MedleyDB) demonstrate that STCA can achieve comparable performance with other state-of-the-art algorithms with simpler architectures. Furthermore, STCA successfully discovers predictive sensory features and shows the highest performance in the unsegmented sensory event detection tasks.

PDF Details