While Reinforcement Learning (RL) provides a promising paradigm for agile locomotion skills with vision inputs in simulation, it is still very challenging to deploy the RL policy in the real world.
There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors.
In this paper, we propose a new platform and pipeline, DexMV (Dexterous Manipulation from Videos), for imitation learning to bridge the gap between computer vision and robot learning.
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images.
Our key insight is that proprioceptive states only offer contact measurements for immediate reaction, whereas an agent equipped with visual sensory observations can learn to proactively maneuver environments with obstacles and uneven terrain by anticipating changes in the environment many steps ahead.
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE).
While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other.
Ranked #1 on Meta-Learning on MT50
Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI.
Based on that, We proposed an end-to-end algorithm to learn exploration policy by meta-learning.
Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation.
1 code implementation • 7 Feb 2019 • Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaśkowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salathé, Sergey Levine, Scott Delp
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly.