3 Hits in 3.4 sec

Tianshou: a Highly Modularized Deep Reinforcement Learning Library [article]

Jiayi Weng, Huayu Chen, Dong Yan, Kaichao You, Alexis Duburcq, Minghao Zhang, Hang Su, Jun Zhu
2021 arXiv   pre-print
We present Tianshou, a highly modularized python library for deep reinforcement learning (DRL) that uses PyTorch as its backend.  ...  Tianshou provides a flexible, reliable, yet simple implementation of a modular DRL library, and has supported more than 20 classic algorithms succinctly through a unified interface.  ...  Acknowledgments We thank Haosheng Zou for his pioneering work of TensorFlow-based Tianshou before version 0.1.1.  ... 
arXiv:2107.14171v2 fatcat:wutwzwu4dnfptaf2dgqsg2fto4

A Survey on Reinforcement Learning Methods in Character Animation [article]

Ariel Kwiatkowski, Eduardo Alvarado, Vicky Kalogeiton, C. Karen Liu, Julien Pettré, Michiel van de Panne, Marie-Paule Cani
2022 arXiv   pre-print
This paper surveys the modern Deep Reinforcement Learning methods and discusses their possible applications in Character Animation, from skeletal control of a single, physically-based character to navigation  ...  Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment.  ...  During this process, the agent progressively trains its own controller module, which in the case of Deep Reinforcement Learning (DRL) is represented by a deep neural network.  ... 
arXiv:2203.04735v1 fatcat:usnqama2frfwxijpctt6bipivu

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

Jiajing Zhang, Yongwei Miao, Jinhui Yu
2021 IEEE Access  
highly negative emotion and 7 meant a highly positive emotion.  ...  The works of [119] , [120] proposed a GAN-based reinforcement learning model to directly learn the filters in a proper sequence with suitable parameters.  ...  This work is licensed under a Creative Commons Attribution 4.0 License.  ... 
doi:10.1109/access.2021.3083075 fatcat:zukn4uhlinejjdubdezsdghh5i