Hiring： Our lab has several Ph.D. and Master positions. If you are interested in our research, please send us your CV (jianye.hao@tju.edu.cn / yanzheng@tju.edu.cn) 实验室长期接受优秀同学交流学习，攻读硕士/博士学位的同学加入。同时欢迎感兴趣学部（院）夏令营活动的同学进行邮件联系！智能与计算学部夏令营活动通知

新闻

News

Jan 21, 2023： Seven papers accepted by ICLR 2023: "ERL-Re2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation", "Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework", "EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model", "Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection", "DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks", "CFlowNets: Continuous control with Generative Flow Network", "Out-of-distribution Detection with Implicit Outlier Transformation"

Nov 25, 2022： Four papers accepted by AAAI 2023: "SplitNet: A Reinforcement Learning based Sequence Splitting Method for the MinMax Multiple Travelling Salesman Problem", "Neighbor Auto-Grouping Graph Neural Networks for Handover Parameter Configuration in Cellular Network", "Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems", "Models as Agents: Optimizing Muti-Step Predictions of interactive Local Models in Model-Based Multi-Agent Reinforcement Learning"

Sep 15, 2022： Seven papers accepted by NeurIPS 2022: "Multiagent Q-learning with Sub-Team Coordination", "Transformer-based Working Memory for Multiagent Reinforcement Learning with Action Parsing", "GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis", "Versatile Multi-stage Graph Neural Network for Circuit Representation", "The Policy-gradient Placement and Generative Routing Neural Networks for Chip Design", "DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning", "Plan To Predict: Learning an Uncertainty-Foreseeing Model For Model-Based Reinforcement Learning"

May 18, 2022： Five papers accepted by ICML 2022: "PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration", "Individual Reward Assisted Multi-Agent Reinforcement Learning", "Plan Your Target and Learn Your Skills: Transferable State-Only lmitation Learning via Decoupled Policy Optimization", "Neuro-Symbolic Hierarchical Rule Induction", "Learning Pseudometric-based Action Representations for Offline Reinforcement Learning"

Apr 21, 2022： One paper accepted by IJCAI 2022: "PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations"

Jan 28, 2022： Three papers accepted by ICLR 2022: "HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation", "Online Ad Hoc Teamwork under Partial Observability", "Learning State Representations via Retracing in Reinforcement Learning"

Dec 1, 2021： One paper accepted by AAAI 2022: "What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator"

Nov 9, 2021： Runner-up, Best Paper Award in PRICAI 2021: "Detecting and Learning Against Unknown Opponents for Automated Negotiations"

Oct 1, 2021： Six papers accepted by NeurIPS 2021: "Dynamic Bottleneck for Robust Self-Supervised Exploration", "Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning", "Model-Based Reinforcement Learning via Imagination with Derived Memory", "A Reinforcement Learning Based Bi-level Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems"， "Adaptive Online Packing-guided Search for POMDPs", "An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning"

Jun 5, 2021： One paper accepted by ICML 2021: " Principled Exploration via Optimistic Bootstrapping and Backward Induction"

May 22, 2021： One paper accepted by KDD 2021: " A Multi-Graph Attributed Reinforcement Learning based Optimization Algorithm for Large-scale Hybrid Flow Shop Scheduling Problem"

Apr 30, 2021： One paper accepted by IJCAI 2021: " Ordering-Based Causal Discovery with Reinforcement Learning"

Apr 27, 2021： One paper accepted by IEEE Transaction on Smart Grid 2021: " Vulnerability Assessment of Deep Reinforcement Learning Models for Power System Topology Optimization"

Jan 1, 2021： One paper accepted by ICSE 2021: " Automatic Web Testing using Curiosity-Driven Reinforcement Learning"

Dec 4, 2020： Three papers accepted by AAAI 2021: "Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning","Addressing Action Oscillations through Learning Policy Inertia"

Sep 30, 2020： One paper accepted by NeurIPS 2020: "Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping"

Jun 3, 2020： Two papers accepted by ICML 2020: "Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising","Q-value Path Decomposition for Deep Multiagent Reinforcement Learning"

Apr 21, 2020： Five papers accepted by IJCAI 2020: "Learning to Accelerate Heuristic Searching for Large-Scale MaximumWeighted b-Matching Problems in Online Advertising", "Efficient Deep Reinforcement Learning via Adaptive Policy Transfer ", " Generating Behavior-Diverse Game AIs with Evolutionary Multi-Objectives Deep Reinforcement Learning", " Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets"， "KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge"

Oct 22, 2019： ACM SIGSOFT Distinguished Paper Award in ASE 2019:" Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning"

Oct 15, 2019： Best Paper Award in DAI 2019:" Achieving Cooperation Through Deep Multiagent Reinforcement Learning in Sequential Prisoner's Dilemmas"

最新成果

Recent Work

=