activity
20202022
most citedDARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning

8 citations · 14 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG20213 cited

Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning

Jinxin Liu, Hao Shen, Donglin Wang +2

Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals an…

cs.LG2021

Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain

Yachen Kang, Jinxin Liu, Xin Cao +1

We propose an approach for inverse reinforcement learning from hetero-domain which learns a reward function in the simulator, drawing on the demonstrations from the real world. The…

cs.LG2021

Adaptive Adversarial Training for Meta Reinforcement Learning

Shiqi Chen, Zhengyu Chen, Donglin Wang

Meta Reinforcement Learning (MRL) enables an agent to learn from a limited number of past trajectories and extrapolate to a new task. In this paper, we attempt to improve the robus…

cs.CV20212 cited

Pareto Self-Supervised Training for Few-Shot Learning

Zhengyu Chen, Jixie Ge, Heshen Zhan +2

While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed…

cs.RO20211 cited

Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning

Ting Wang, Zongkai Wu, Donglin Wang

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual i…

cs.CV2020

Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition

Siteng Huang, Min Zhang, Yachen Kang +1

The purpose of few-shot recognition is to recognize novel categories with a limited number of labeled examples in each class. To encourage learning from a supplementary view, recen…