Pearl: A Production-ready Reinforcement Learning Agent

1 code implementation • 6 Dec 2023 • Zheqing Zhu, Rodrigo de Salvo Braz, Jalaj Bhandari, Daniel Jiang, Yi Wan, Yonathan Efroni, Liyuan Wang, Ruiyang Xu, Hongbo Guo, Alex Nikulkov, Dmytro Korenkevych, Urun Dogan, Frank Cheng, Zheng Wu, Wanqiao Xu

Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals.

reinforcement-learning Reinforcement Learning (RL)

Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward

no code implementations • 3 Dec 2022 • Yanjiang Guo, Jingyue Gao, Zheng Wu, Chengming Shi, Jianyu Chen

In this paper, we consider the case where the target task is mismatched from but similar with that of the expert.

reinforcement-learning Reinforcement Learning (RL) +1

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

no code implementations • 1 Oct 2022 • Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal, Masayoshi Tomizuka

Experimental results demonstrate that our proposed method achieves policy generalization to unseen compositional tasks in a zero-shot manner.

Disentanglement Meta Reinforcement Learning +2

ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale

no code implementations • 19 Jul 2022 • Gopinath Chennupati, Milind Rao, Gurpreet Chadha, Aaron Eakin, Anirudh Raju, Gautam Tiwari, Anit Kumar Sahu, Ariya Rastrow, Jasha Droppo, Andy Oberlin, Buddha Nandanoor, Prahalad Venkataramanan, Zheng Wu, Pankaj Sitpure

For end-to-end automatic speech recognition (ASR) tasks, the absence of human annotated labels along with the need for privacy preserving policies for model building makes it a daunting challenge.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Expressing Diverse Human Driving Behavior with Probabilistic Rewards and Online Inference

no code implementations • 20 Aug 2020 • Liting Sun, Zheng Wu, Hengbo Ma, Masayoshi Tomizuka

In human-robot interaction (HRI) systems, such as autonomous vehicles, understanding and representing human behavior are important.

Autonomous Vehicles

Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving

no code implementations • 22 Jun 2020 • Zheng Wu, Liting Sun, Wei Zhan, Chenyu Yang, Masayoshi Tomizuka

Different from existing IRL algorithms, by introducing an efficient continuous-domain trajectory sampler, the proposed algorithm can directly learn the reward functions in the continuous domain while considering the uncertainties in demonstrated trajectories from human drivers.

Autonomous Driving reinforcement-learning +1

Learning to Describe Scenes with Programs

no code implementations • ICLR 2019 • Yunchao Liu, Zheng Wu, Daniel Ritchie, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

We are able to understand the higher-level, abstract regularities within the scene such as symmetry and repetition.

Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters

no code implementations • 1 Feb 2018 • Zheng Wu, Ruiheng Chang, Jiaxu Ma, Cewu Lu, Chi-Keung Tang

We propose a novel approach for instance segmen- tation given an image of homogeneous object clus- ter (HOC).

Instance Segmentation One-Shot Learning +1

Class Probability Estimation via Differential Geometric Regularization

no code implementations • 4 Mar 2015 • Qinxun Bai, Steven Rosenberg, Zheng Wu, Stan Sclaroff

We study the problem of supervised learning for both binary and multiclass classification from a unified geometric perspective.

Classification General Classification