Yujing Hu
Research Subjects
Yujing Hu has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
- Changjie Fan
NetEase Fuxi AI Lab, Hangzhou, China
12 shared publications - Jianye Hao
Tianjin University, Tianjin, China
9 shared publications - Yang Gao
Nanjing University
6 shared publications - Yingfeng Chen
Fuxi AI Lab in Netease
6 shared publications - Tangjie Lv
NetEase Fuxi AI Lab, Hangzhou, China
5 shared publications - Weixun Wang
College of Intelligence and Computing Tianjin University
5 shared publications
Latest Publications
- 12 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106858
Coordinating Multi-Agent Reinforcement Learning via Dual Collaborative Constraints
- 12 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106858
Coordinating Multi-Agent Reinforcement Learning via Dual Collaborative Constraints
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 5689-5697
Federated Domain Generalization with Decision Insight Matrix
Federated domain generalization addresses the crucial challenge of developing models that can generalize across diverse domains while maintaining data privacy in federated learning settings. Current approaches either compromise privacy constraints or focus narrowly on specific aspects of model invariance, often incurring significant computational overhead. We propose a novel approach FedDIM, which leverages the concept of “insight matrix” - a fine-grained representation of the model's decision-making process derived from element-wise products between feature vectors and classifier weights. By introducing a regularization term that promotes consistency between individual sample insight matrices and their class-wise mean representations, our method effectively captures both feature and classifier invariance. This approach not only maintains strict privacy requirements but also introduces minimal computational overhead as it utilizes intermediate computations already present in the forward pass. Extensive experiments demonstrate that our method achieves superior out-of-distribution generalization compared to existing federated learning approaches while being simple to implement. Our work provides a new perspective on achieving robust generalization in federated learning settings through the lens of decision-making processes.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 6, 5689-5697
Open AccessFederated Domain Generalization with Decision Insight Matrix
Federated domain generalization addresses the crucial challenge of developing models that can generalize across diverse domains while maintaining data privacy in federated learning settings. Current approaches either compromise privacy constraints or focus narrowly on specific aspects of model invariance, often incurring significant computational overhead. We propose a novel approach FedDIM, which leverages the concept of “insight matrix” - a fine-grained representation of the model's decision-making process derived from element-wise products between feature vectors and classifier weights. By introducing a regularization term that promotes consistency between individual sample insight matrices and their class-wise mean representations, our method effectively captures both feature and classifier invariance. This approach not only maintains strict privacy requirements but also introduces minimal computational overhead as it utilizes intermediate computations already present in the forward pass. Extensive experiments demonstrate that our method achieves superior out-of-distribution generalization compared to existing federated learning approaches while being simple to implement. Our work provides a new perspective on achieving robust generalization in federated learning settings through the lens of decision-making processes.
- Open Access
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL.
Open AccessvMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with many efforts focused on using ensemble critics to boost policy evaluation efficiency. However, when using multiple critics, the actor in the policy improvement process can obtain different gradients. Previous studies have combined these gradients without considering their disagreements. Therefore, optimizing the policy improvement process is crucial to enhance learning efficiency. This study focuses on investigating the impact of gradient disagreements caused by ensemble critics on policy improvement. We introduce the concept of uncertainty of gradient directions as a means to measure the disagreement among gradients utilized in the policy improvement process. Through measuring the disagreement among gradients, we find that transitions with lower uncertainty of gradient directions are more reliable in the policy improvement process. Building on this analysis, we propose a method called von Mises-Fisher Experience Resampling (vMFER), which optimizes the policy improvement process by resampling transitions and assigning higher confidence to transitions with lower uncertainty of gradient directions. Our experiments demonstrate that vMFER significantly outperforms the benchmark and is particularly well-suited for ensemble structures in RL.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (16) , 17453-17460
Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning, decentralized agents hold the promise of overcoming the combinatorial explosion of joint action space and enabling greater scalability. However, they are susceptible to a game-theoretic pathology called relative overgeneralization that shadows the optimal joint action. Although recent value-decomposition algorithms guide decentralized agents by learning a factored global action value function, the representational limitation and the inaccurate sampling of optimal joint actions during the learning process make this problem still. To address this limitation, this paper proposes a novel algorithm called Optimistic Value Instructors (OVI). The main idea behind OVI is to introduce multiple optimistic instructors into the value-decomposition paradigm, which are capable of suggesting potentially optimal joint actions and rectifying the factored global action value function to recover these optimal actions. Specifically, the instructors maintain optimistic value estimations of per-agent local actions and thus eliminate the negative effects caused by other agents' exploratory or sub-optimal non-cooperation, enabling accurate identification and suggestion of optimal joint actions. Based on the instructors' suggestions, the paper further presents two instructive constraints to rectify the factored global action value function to recover these optimal joint actions, thus overcoming the RO problem. Experimental evaluation of OVI on various cooperative multi-agent tasks demonstrates its superior performance against multiple baselines, highlighting its effectiveness.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (16) , 17453-17460
Open AccessOptimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning
In cooperative multi-agent reinforcement learning, decentralized agents hold the promise of overcoming the combinatorial explosion of joint action space and enabling greater scalability. However, they are susceptible to a game-theoretic pathology called relative overgeneralization that shadows the optimal joint action. Although recent value-decomposition algorithms guide decentralized agents by learning a factored global action value function, the representational limitation and the inaccurate sampling of optimal joint actions during the learning process make this problem still. To address this limitation, this paper proposes a novel algorithm called Optimistic Value Instructors (OVI). The main idea behind OVI is to introduce multiple optimistic instructors into the value-decomposition paradigm, which are capable of suggesting potentially optimal joint actions and rectifying the factored global action value function to recover these optimal actions. Specifically, the instructors maintain optimistic value estimations of per-agent local actions and thus eliminate the negative effects caused by other agents' exploratory or sub-optimal non-cooperation, enabling accurate identification and suggestion of optimal joint actions. Based on the instructors' suggestions, the paper further presents two instructive constraints to rectify the factored global action value function to recover these optimal joint actions, thus overcoming the RO problem. Experimental evaluation of OVI on various cooperative multi-agent tasks demonstrates its superior performance against multiple baselines, highlighting its effectiveness.
- 4 December 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (24) , 31129-31164
Deep learning applications in games: a survey from a data perspective
- 4 December 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (24) , 31129-31164
Deep learning applications in games: a survey from a data perspective
- 10 November 2023
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 37 (2) , 1-37
ASN: action semantics network for multiagent reinforcement learning
- 10 November 2023
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 37 (2) , 1-37
ASN: action semantics network for multiagent reinforcement learning
- 25 May 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (2) , 6161-6182
Promoting human-AI interaction makes a better adoption of deep reinforcement learning: a real-world application in game industry
- 25 May 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (2) , 6161-6182
Promoting human-AI interaction makes a better adoption of deep reinforcement learning: a real-world application in game industry
- Open Access
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms to solve tasks with hard-to-specify reward functions in Minecraft. Through this competition, we aimed to promote the development of algorithms that use human feedback as channels to learn the desired behavior. We describe the competition and provide an overview of the top solutions. We conclude by discussing the impact of the competition and future directions for improvement.
Open AccessTowards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms to solve tasks with hard-to-specify reward functions in Minecraft. Through this competition, we aimed to promote the development of algorithms that use human feedback as channels to learn the desired behavior. We describe the competition and provide an overview of the top solutions. We conclude by discussing the impact of the competition and future directions for improvement.
- Open Access
Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning
Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods are among those cutting-edge solutions. However, traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. This hinders their application in generic scenarios. Recent methods tackle this problem from the perspective of implicit credit assignment by learning value functions with complete expressiveness or using additional structures to improve cooperation. However, they are either difficult to learn due to large joint action spaces or insufficient to capture the complicated interactions among agents which are essential to solving tasks with non-monotonic returns. To address these problems, we propose a novel explicit credit assignment method to address the non-monotonic problem. Our method, Adaptive Value decomposition with Greedy Marginal contribution (AVGM), is based on an adaptive value decomposition that learns the cooperative value of a group of dynamically changing agents. We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios. Then, our method uses a greedy marginal contribution computed from the value decomposition as an individual credit to incentivize agents to learn the optimal cooperative policy. We further extend the module with an action encoder to guarantee the linear time complexity for computing the greedy marginal contribution. Experimental results demonstrate that our method achieves significant performance improvements in several non-monotonic domains.
Open AccessAdaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning
Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods are among those cutting-edge solutions. However, traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. This hinders their application in generic scenarios. Recent methods tackle this problem from the perspective of implicit credit assignment by learning value functions with complete expressiveness or using additional structures to improve cooperation. However, they are either difficult to learn due to large joint action spaces or insufficient to capture the complicated interactions among agents which are essential to solving tasks with non-monotonic returns. To address these problems, we propose a novel explicit credit assignment method to address the non-monotonic problem. Our method, Adaptive Value decomposition with Greedy Marginal contribution (AVGM), is based on an adaptive value decomposition that learns the cooperative value of a group of dynamically changing agents. We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios. Then, our method uses a greedy marginal contribution computed from the value decomposition as an individual credit to incentivize agents to learn the optimal cooperative policy. We further extend the module with an action encoder to guarantee the linear time complexity for computing the greedy marginal contribution. Experimental results demonstrate that our method achieves significant performance improvements in several non-monotonic domains.
- Open Access
An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning
Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option module can only collect all agent's local experiences for update due to the partial observability of the environment. While in this setting, each agent's experience may be inconsistent with each other, which may cause the inaccuracy and oscillation of the option-value's estimation. Therefore, we propose a novel option learning algorithm, the successor representation option learning to solve it by decoupling the environment dynamics from rewards and learning the option-value under each agent's preference. MAPTF can be easily combined with existing deep RL and MARL approaches, and experimental results show it significantly boosts the performance of existing methods in both discrete and continuous state spaces.
Open AccessAn Efficient Transfer Learning Framework for Multiagent Reinforcement Learning
Transfer Learning has shown great potential to enhance single-agent Reinforcement Learning (RL) efficiency. Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other. However, it remains a problem of how an agent should learn from other agents. In this paper, we propose a novel Multiagent Policy Transfer Framework (MAPTF) to improve MARL efficiency. MAPTF learns which agent's policy is the best to reuse for each agent and when to terminate it by modeling multiagent policy transfer as the option learning problem. Furthermore, in practice, the option module can only collect all agent's local experiences for update due to the partial observability of the environment. While in this setting, each agent's experience may be inconsistent with each other, which may cause the inaccuracy and oscillation of the option-value's estimation. Therefore, we propose a novel option learning algorithm, the successor representation option learning to solve it by decoupling the environment dynamics from rewards and learning the option-value under each agent's preference. MAPTF can be easily combined with existing deep RL and MARL approaches, and experimental results show it significantly boosts the performance of existing methods in both discrete and continuous state spaces.