Search Results for author: Dongbin Zhao

Found 31 papers, 7 papers with code

StarCraft Micromanagement with Reinforcement Learning and Curriculum Transfer Learning

1 code implementation3 Apr 2018 Kun Shao, Yuanheng Zhu, Dongbin Zhao

With reinforcement learning and curriculum transfer learning, our units are able to learn appropriate strategies in StarCraft micromanagement scenarios.

reinforcement-learning Reinforcement Learning (RL) +2

Reinforcement Learning and Deep Learning based Lateral Control for Autonomous Driving

1 code implementation30 Oct 2018 Dong Li, Dongbin Zhao, Qichao Zhang, Yaran Chen

The control module which is based on reinforcement learning then makes a control decision based on these features.

Autonomous Driving Model Predictive Control +3

Lane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints

no code implementations30 Mar 2019 Jun-Jie Wang, Qichao Zhang, Dongbin Zhao, Yaran Chen

Autonomous driving decision-making is a great challenge due to the complexity and uncertainty of the traffic environment.

Autonomous Driving Decision Making +2

Graph Attention Memory for Visual Navigation

no code implementations11 May 2019 Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Bin Wang, Wulong Liu, Rasul Tutunov, Jun Wang

To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module.

Graph Attention Reinforcement Learning (RL) +1

A Survey of Deep Reinforcement Learning in Video Games

no code implementations23 Dec 2019 Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao

In this paper, we survey the progress of DRL methods, including value-based, policy gradient, and model-based algorithms, and compare their main techniques and properties.

Real-Time Strategy Games reinforcement-learning +1

Graph-FCN for image semantic segmentation

no code implementations2 Jan 2020 Yi Lu, Yaran Chen, Dongbin Zhao, Jianxin Chen

Then we apply graph convolutional network to solve this graph node classification problem.

General Classification Node Classification +2

BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture

no code implementations18 Jan 2020 Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao, Zhiquan Sun, C. L. Philip Chen

In this paper, we propose Broad Neural Architecture Search (BNAS) where we elaborately design broad scalable architecture dubbed Broad Convolutional Neural Network (BCNN) to solve the above issue.

Neural Architecture Search reinforcement-learning +1

Enhanced Rolling Horizon Evolution Algorithm with Opponent Model Learning: Results for the Fighting Game AI Competition

no code implementations31 Mar 2020 Zhentao Tang, Yuanheng Zhu, Dongbin Zhao, Simon M. Lucas

In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent.

Q-Learning

ModuleNet: Knowledge-inherited Neural Architecture Search

no code implementations10 Apr 2020 Yaran Chen, Ruiyuan Gao, Fenggang Liu, Dongbin Zhao

Unlike previous search algorithms, and benefiting from inherited knowledge, our method is able to directly search for architectures in the macro space by NSGA-II algorithm without tuning parameters in these \textit{module}s. Experiments show that our strategy can efficiently evaluate the performance of new architecture even without tuning weights in convolutional layers.

Neural Architecture Search

BiFNet: Bidirectional Fusion Network for Road Segmentation

no code implementations18 Apr 2020 Haoran Li, Yaran Chen, Qichao Zhang, Dongbin Zhao

Considering the bird's eye views(BEV) of the LiDAR remains the space structure in horizontal plane, this paper proposes a bidirectional fusion network(BiFNet) to fuse the image and BEV of the point cloud.

Road Segmentation Sensor Fusion

BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search

no code implementations18 Sep 2020 Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao

For this consequent issue, two solutions are given: 1) we propose Confident Learning Rate (CLR) that considers the confidence of gradient for architecture weights update, increasing with the training time of over-parameterized BCNN; 2) we introduce the combination of partial channel connections and edge normalization that also can improve the memory efficiency further.

Neural Architecture Search

Dynamic Horizon Value Estimation for Model-based Reinforcement Learning

no code implementations21 Sep 2020 Jun-Jie Wang, Qichao Zhang, Dongbin Zhao, Mengchen Zhao, Jianye Hao

Existing model-based value expansion methods typically leverage a world model for value estimation with a fixed rollout horizon to assist policy learning.

Model-based Reinforcement Learning Novelty Detection +2

Heuristic Rank Selection with Progressively Searching Tensor Ring Network

no code implementations22 Sep 2020 Nannan Li, Yu Pan, Yaran Chen, Zixiang Ding, Dongbin Zhao, Zenglin Xu

Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region.

Event-Triggered Multi-agent Reinforcement Learning with Communication under Limited-bandwidth Constraint

no code implementations10 Oct 2020 Guangzheng Hu, Yuanheng Zhu, Dongbin Zhao, Mengchen Zhao, Jianye Hao

Then the design of the event-triggered strategy is formulated as a constrained Markov decision problem, and reinforcement learning finds the best communication protocol that satisfies the limited bandwidth constraint.

Multiagent Systems

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

1 code implementation22 Sep 2021 Yuqi Liu, Qichao Zhang, Dongbin Zhao

The test benchmark and baselines are to provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing the progress of RL-based methods for intersection autonomous driving control.

Autonomous Driving reinforcement-learning +1

Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning

no code implementations22 Sep 2021 Junjie Wang, Qichao Zhang, Dongbin Zhao

We train several state-of-the-art deep reinforcement learning methods in the designed training scenarios and provide the benchmark metrics evaluation results of the trained models in the test scenarios.

Autonomous Driving Benchmarking +4

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

no code implementations15 Nov 2021 Zixiang Ding, Yaran Chen, Nannan Li, Dongbin Zhao, C. L. Philip Chen

Moreover, multi-scale feature fusion and knowledge embedding are proposed to improve the performance of BCNN with shallow topology.

Neural Architecture Search

BViT: Broad Attention based Vision Transformer

1 code implementation13 Feb 2022 Nannan Li, Yaran Chen, Weifan Li, Zixiang Ding, Dongbin Zhao

In this paper, we propose the broad attention to improve the performance by incorporating the attention relationship of different layers for vision transformer, which is called BViT.

Image Classification Object Recognition

Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

no code implementations19 Feb 2022 Yuqi Liu, Qichao Zhang, Dongbin Zhao

In this paper, we formulate a multi-task safe reinforcement learning with social attention to improve the safety and efficiency when interacting with other traffic participants.

Autonomous Driving reinforcement-learning +2

Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation

no code implementations19 Oct 2022 Ding Li, Qichao Zhang, Shuai Lu, Yifeng Pan, Dongbin Zhao

Our CGTP framework is an end to end and interpretable model, including three main stages: context encoding, goal interactive prediction and trajectory interactive prediction.

Motion Forecasting Trajectory Forecasting

Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning

no code implementations23 Nov 2022 Junjie Wang, Yao Mu, Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Ping Luo, Bin Wang, Jianye Hao

The latent world model provides a promising way to learn policies in a compact latent space for tasks with high-dimensional observations, however, its generalization across diverse environments with unseen dynamics remains challenging.

Model-based Reinforcement Learning reinforcement-learning +1

A Hierarchical Deep Reinforcement Learning Framework for 6-DOF UCAV Air-to-Air Combat

no code implementations5 Dec 2022 Jiajun Chai, Wenzhang Chen, Yuanheng Zhu, Zong-xin Yao, Dongbin Zhao

Then the inner loop tracks the macro behavior with a flight controller by calculating the actual input signals for the aircraft.

Reinforcement Learning (RL)

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning

no code implementations11 Feb 2023 Xin Liu, Yaran Chen, Haoran Li, Boyu Li, Dongbin Zhao

CRPTpro significantly outperforms the next best Proto-RL(C) on 11/12 cross-domain downstream tasks with only 54\% wall-clock pre-training time, exhibiting state-of-the-art pre-training performance with greatly improved pre-training efficiency.

reinforcement-learning Reinforcement Learning (RL) +1

Multi-modal Learning based Prediction for Disease

no code implementations19 Jul 2023 Yaran Chen, Xueyu Chen, Yu Han, Haoran Li, Dongbin Zhao, Jingzhong Li, Xu Wang

From the dataset, we quantitatively analyze and select clinical metadata that most contribute to NAFLD prediction.

ComSD: Balancing Behavioral Quality and Diversity in Unsupervised Skill Discovery

1 code implementation29 Sep 2023 Xin Liu, Yaran Chen, Dongbin Zhao

Ideal unsupervised skill discovery methods are able to produce diverse and qualified skills in the absence of extrinsic reward, while the discovered skill set can efficiently adapt to downstream tasks in various ways.

Contrastive Learning

Boosting Continuous Control with Consistency Policy

1 code implementation10 Oct 2023 Yuhui Chen, Haoran Li, Dongbin Zhao

By establishing a mapping from the reverse diffusion trajectories to the desired policy, we simultaneously address the issues of time efficiency and inaccurate guidance when updating diffusion model-based policy with the learned Q-function.

Continuous Control Q-Learning +1

RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks

no code implementations27 Nov 2023 Yaran Chen, Wenbo Cui, Yuanwen Chen, Mining Tan, Xinyao Zhang, Dongbin Zhao, He Wang

To address the problem, we propose a RoboGPT agent\footnote{our code and dataset will be released soon} for making embodied long-term decisions for daily tasks, with two modules: 1) LLMs-based planning with re-plan to break the task into multiple sub-goals; 2) RoboSkill individually designed for sub-goals to learn better navigation and manipulation skills.

Common Sense Reasoning

FM3Q: Factorized Multi-Agent MiniMax Q-Learning for Two-Team Zero-Sum Markov Game

no code implementations1 Feb 2024 Guangzheng Hu, Yuanheng Zhu, Haoran Li, Dongbin Zhao

Based on it, we present a novel multi-agent reinforcement learning framework, Factorized Multi-Agent MiniMax Q-Learning (FM3Q), which can factorize the joint minimax Q function into individual ones and iteratively solve for the IGMM-satisfied minimax Q functions for 2t0sMGs.

Multi-agent Reinforcement Learning Q-Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.