Author name cluster

Yali Du 0001

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.

14 papers

1 author row

ICML Conference 2025 Conference Paper

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs

Yue Wang
Qizhou Wang
Feng Liu 0003
Wei Huang 0034
Yali Du 0001
Xiaojiang Du
Bo Han 0003

Large language model (LLM) unlearning has demonstrated its essential role in removing privacy and copyright-related responses, crucial for their legal and safe applications. However, the pursuit of complete unlearning often comes with substantial costs due to its compromises in their general functionality, leading to a notorious trade-off between unlearning and retention. It motivates this paper to explore enhanced unlearning schemes that can mitigate this trade-off. Specifically, we propose Gradient Rectified Unlearning (GRU), an improved framework that regulates the directions of gradient updates during the unlearning procedure such that their side impacts on other, unrelated responses can be minimized. GRU is easy and general to implement, demonstrating practical effectiveness across a variety of well-established unlearning benchmarks.

Details

ICML Conference 2025 Conference Paper

M³HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality

Ziyan Wang
Zhicheng Zhang
Fei Fang 0001
Yali Du 0001

Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\text{M}^3\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\text{M}^3\text{HF}$ leverages both expert and non-expert feedback to continuously refine agents’ policies. During training, we strategically pause agent learning for human evaluation, parse feedback using large language models to assign it appropriately and update reward functions through predefined templates and adaptive weights by using weight decay and performance-based adjustments. Our approach enables the integration of nuanced human insights across various levels of quality, enhancing the interpretability and robustness of multi-agent cooperation. Empirical results in challenging environments demonstrate that $\text{M}^3\text{HF}$ significantly outperforms state-of-the-art methods, effectively addressing the complexities of reward design in MARL and enabling broader human participation in the training process.

Details

ICLR Conference 2025 Conference Paper

On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

Xu-Hui Liu
Yali Du 0001
Jun Wang 0012
Yang Yu 0001

Training Large Language Models (LLMs) poses significant memory challenges, making low-rank adaptation methods an attractive solution. Previously, Low-Rank Adaptation (LoRA) addressed this by adding a trainable low-rank matrix to the frozen pre-trained weights in each layer, reducing the number of trainable parameters and optimizer states. GaLore, which compresses the gradient matrix instead of the weight matrix, has demonstrated superior performance to LoRA with faster convergence and reduced memory consumption. Despite their empirical success, the performance of these methods has not been fully understood or explained theoretically. In this paper, we analyze the optimization landscapes of LoRA, GaLore, and full-rank methods, revealing that GaLore benefits from fewer spurious local minima and a larger region that satisfies the \pl, a variant of Polyak-Łojasiewicz (PL) condition, leading to faster convergence. Our analysis leads to a novel method, GaRare, which further improves GaLore by using gradient random projection to reduce computational overhead. Practically, GaRare achieves strong performance in both pre-training and fine-tuning tasks, offering a more efficient approach to large-scale model adaptation.

Details

ICLR Conference 2025 Conference Paper

RuAG: Learned-rule-augmented Generation for Large Language Models

Yudi Zhang 0006
Pei Xiao 0007
Lu Wang 0029
Chaoyun Zhang
Meng Fang
Yali Du 0001
Yevgeniy Puzyrev
Randolph Yao

In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, we apply Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including Natural Language Processing (NLP), time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.

Details

ICRA Conference 2024 Conference Paper

Characterizing Physical Adversarial Attacks on Robot Motion Planners

Wenxi Wu
Fabio Pierazzi
Yali Du 0001
Martim Brandão

As the adoption of robots across society increases, so does the importance of considering cybersecurity issues such as vulnerability to adversarial attacks. In this paper we investigate the vulnerability of an important component of autonomous robots to adversarial attacks—robot motion planning algorithms. We particularly focus on attacks on the physical environment, and propose the first such attacks to motion planners: “planner failure” and “blindspot” attacks. Planner failure attacks make changes to the physical environment so as to make planners fail to find a solution. Blindspot attacks exploit occlusions and sensor field-of-view to make planners return a trajectory which is thought to be collision-free, but is actually in collision with unperceived parts of the environment. Our experimental results show that successful attacks need only to make subtle changes to the real world, in order to obtain a drastic increase in failure rates and collision rates—leading the planner to fail 95% of the time and collide 90% of the time in problems generated with an existing planner benchmark tool. We also analyze the transferability of attacks to different planners, and discuss underlying assumptions and future research directions. Overall, the paper shows that physical adversarial attacks on motion planning algorithms pose a serious threat to robotics, which should be taken into account in future research and development.

Details

ECAI Conference 2024 Conference Paper

Explaining an Agent's Future Beliefs Through Temporally Decomposing Future Reward Estimators

Mark Towers
Yali Du 0001
Christopher T. Freeman
Timothy J. Norman

Future reward estimation is a core component of reinforcement learning agents; i. e. , Q-value and state-value functions, predicting an agent’s sum of future rewards. Their scalar output, however, obfuscates when or what individual future rewards an agent may expect to receive. We address this by modifying an agent’s future reward estimator to predict their next N expected rewards, referred to as Temporal Reward Decomposition (TRD). This unlocks novel explanations of agent behaviour. Through TRD we can: estimate when an agent may expect to receive a reward, the value of the reward and the agent’s confidence in receiving it; measure an input feature’s temporal importance to the agent’s action decisions; and predict the influence of different actions on future rewards. Furthermore, we show that DQN agents trained on Atari environments can be efficiently retrained to incorporate TRD with minimal impact on performance.

Details

ICML Conference 2024 Conference Paper

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

Runze Liu 0002
Yali Du 0001
Fengshuo Bai
Jiafei Lyu
Xiu Li 0001

In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot be utilized for the new tasks. In this paper, we propose Zero-shot Cross-task Preference Alignment and Robust Reward Learning (PEARL), which learns policies from cross-task preference transfer without any human labels of the target task. Our contributions include two novel components that facilitate the transfer and learning process. The first is Cross-task Preference Alignment (CPA), which transfers the preferences between tasks via optimal transport. The key idea of CPA is to use Gromov-Wasserstein distance to align the trajectories between tasks, and the solved optimal transport matrix serves as the correspondence between trajectories. The target task preferences are computed as the weighted sum of source task preference labels with the correspondence as weights. Moreover, to ensure robust learning from these transferred labels, we introduce Robust Reward Learning (RRL), which considers both reward mean and uncertainty by modeling rewards as Gaussian distributions. Empirical results on robotic manipulation tasks from Meta-World and Robomimic demonstrate that our method is capable of transferring preference labels across tasks accurately and then learns well-behaved policies. Notably, our approach significantly exceeds existing methods when there are few human preferences. The code and videos of our method are available at: https: //sites. google. com/view/pearl-preference.

Details

ICML Conference 2023 Conference Paper

Cooperative Open-ended Learning Framework for Zero-Shot Coordination

Yang Li 0116
Shao Zhang
Jichen Sun
Yali Du 0001
Ying Wen 0001
Xinbing Wang
Wei Pan 0004

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by optimizing fixed objectives within a population to improve strategy or behaviour diversity. However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility. To address this issue, we propose the Cooperative Open-ended LEarning (COLE) framework, which constructs open-ended objectives in cooperative games with two players from the perspective of graph theory to assess and identify the cooperative ability of each strategy. We further specify the framework and propose a practical algorithm that leverages knowledge from game theory and graph theory. Furthermore, an analysis of the learning process of the algorithm shows that it can efficiently overcome cooperative incompatibility. The experimental results in the Overcooked game environment demonstrate that our method outperforms current state-of-the-art methods when coordinating with different-level partners. Our demo is available at https: //sites. google. com/view/cole-2023.

Details

ICLR Conference 2023 Conference Paper

Stay Moral and Explore: Learn to Behave Morally in Text-based Games

Zijing Shi
Meng Fang
Yunqiu Xu
Ling Chen 0006
Yali Du 0001

Reinforcement learning (RL) in text-based games has developed rapidly and achieved promising results. However, little effort has been expended to design agents that pursue objectives while behaving morally, which is a critical issue in the field of autonomous agents. In this paper, we propose a general framework named Moral Awareness Adaptive Learning (MorAL) that enhances the morality capacity of an agent using a plugin moral-aware learning model. The framework allows the agent to execute task learning and morality learning adaptively. The agent selects trajectories from past experiences during task learning. Meanwhile, the trajectories are used to conduct self-imitation learning with a moral-enhanced objective. In order to achieve the trade-off between morality and task progress, the agent uses the combination of task policy and moral policy for action selection. We evaluate on the Jiminy Cricket benchmark, a set of text-based games with various scenes and dense morality annotations. Our experiments demonstrate that, compared with strong contemporary value alignment approaches, the proposed framework improves task performance while reducing immoral behaviours in various games.

Details

ICLR Conference 2022 Conference Paper

Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL

Rui Yang 0010
Yiming Lu
Wenzhe Li
Hao Sun
Meng Fang
Yali Du 0001
Xiu Li 0001
Lei Han 0001

Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Conditioned Supervised Learning (GCSL), provides a new learning framework by iteratively relabeling and imitating self-generated experiences. In this paper, we revisit the theoretical property of GCSL --- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm. The proposed method is named Weighted GCSL (WGCSL), in which we introduce an advanced compound weight consisting of three parts (1) discounted weight for goal relabeling, (2) goal-conditioned exponential advantage weight, and (3) best-advantage weight. Theoretically, WGCSL is proved to optimize an equivalent lower bound of the goal-conditioned RL objective and generates monotonically improved policies via an iterated scheme. The monotonic property holds for any behavior policies, and therefore WGCSL can be applied to both online and offline settings. To evaluate algorithms in the offline goal-conditioned RL setting, we provide a benchmark including a range of point and simulated robot domains. Experiments in the introduced benchmark demonstrate that WGCSL can consistently outperform GCSL and existing state-of-the-art offline methods in the fully offline goal-conditioned setting.

Details

IROS Conference 2022 Conference Paper

Scalable Model-based Policy Optimization for Decentralized Networked Systems

Yali Du 0001
Chengdong Ma
Yuchen Liu
Runji Lin
Hao Dong 0003
Jun Wang 0012
Yaodong Yang 0001

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly, requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirical results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models. The source code of our algorithm and baselines can be found at https://github.com/PKU-MARL/Model-Based-MARL.

Details

ICML Conference 2021 Conference Paper

Estimating α-Rank from A Few Entries with Low Rank Matrix Completion

Yali Du 0001
Xue Yan
Xu Chen 0017
Jun Wang 0012
Haifeng Zhang 0002

Multi-agent evaluation aims at the assessment of an agent’s strategy on the basis of interaction with others. Typically, existing methods such as $\alpha$-rank and its approximation still require to exhaustively compare all pairs of joint strategies for an accurate ranking, which in practice is computationally expensive. In this paper, we aim to reduce the number of pairwise comparisons in recovering a satisfying ranking for $n$ strategies in two-player meta-games, by exploring the fact that agents with similar skills may achieve similar payoffs against others. Two situations are considered: the first one is when we can obtain the true payoffs; the other one is when we can only access noisy payoff. Based on these formulations, we leverage low-rank matrix completion and design two novel algorithms for noise-free and noisy evaluations respectively. For both of these settings, we theorize that $O(nr \log n)$ ($n$ is the number of agents and $r$ is the rank of the payoff matrix) payoff entries are required to achieve sufficiently well strategy evaluation performance. Empirical results on evaluating the strategies in three synthetic games and twelve real world games demonstrate that strategy evaluation from a few entries can lead to comparable performance to algorithms with full knowledge of the payoff matrix.

Details

ICML Conference 2021 Conference Paper

Learning in Nonzero-Sum Stochastic Games with Potentials

David Henry Mguni
Yutong Wu 0005
Yali Du 0001
Yaodong Yang 0001
Ziyi Wang 0004
Minne Li
Ying Wen 0001
Joel Jennings

Multi-agent reinforcement learning (MARL) has become effective in tackling discrete cooperative game scenarios. However, MARL has yet to penetrate settings beyond those modelled by team and zero-sum games, confining it to a small subset of multi-agent systems. In this paper, we introduce a new generation of MARL learners that can handle \textit{nonzero-sum} payoff structures and continuous settings. In particular, we study the MARL problem in a class of games known as stochastic potential games (SPGs) with continuous state-action spaces. Unlike cooperative games, in which all agents share a common reward, SPGs are capable of modelling real-world scenarios where agents seek to fulfil their individual goals. We prove theoretically our learning method, $\ourmethod$, enables independent agents to learn Nash equilibrium strategies in \textit{polynomial time}. We demonstrate our framework tackles previously unsolvable tasks such as \textit{Coordination Navigation} and \textit{large selfish routing games} and that it outperforms the state of the art MARL baselines such as MADDPG and COMIX in such scenarios.

Details

ICML Conference 2019 Conference Paper

Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI

Lei Han 0001
Peng Sun 0011
Yali Du 0001
Jiechao Xiong
Qing Wang 0015
Xinghai Sun
Han Liu 0001
Tong Zhang 0001

We consider the problem of multi-agent reinforcement learning (MARL) in video game AI, where the agents are located in a spatial grid-world environment and the number of agents varies both within and across episodes. The challenge is to flexibly control an arbitrary number of agents while achieving effective collaboration. Existing MARL methods usually suffer from the trade-off between these two considerations. To address the issue, we propose a novel architecture that learns a spatial joint representation of all the agents and outputs grid-wise actions. Each agent will be controlled independently by taking the action from the grid it occupies. By viewing the state information as a grid feature map, we employ a convolutional encoder-decoder as the policy network. This architecture naturally promotes agent communication because of the large receptive field provided by the stacked convolutional layers. Moreover, the spatially shared convolutional parameters enable fast parallel exploration that the experiences discovered by one agent can be immediately transferred to others. The proposed method can be conveniently integrated with general reinforcement learning algorithms, e. g. , PPO and Q-learning. We demonstrate the effectiveness of the proposed method in extensive challenging multi-agent tasks in StarCraft II.

Details