Lamarckian Platform: Pushing the Boundaries of Evolutionary Reinforcement Learning towards Asynchronous Commercial Games

no code implementations • 21 Sep 2022 • Hui Bai, Ruimin Shen, Yue Lin, Botian Xu, Ran Cheng

In comparison with the state-of-the-art RLlib, we empirically demonstrate the unique advantages of Lamarckian on benchmark tests with up to 6000 CPU cores: i) both the sampling efficiency and training speed are doubled when running PPO on Google football game; ii) the training speed is 13 times faster when running PBT+PPO on Pong game.

Distributed Computing reinforcement-learning +1

Diverse Behavior Is What Game AI Needs: Generating Varied Human-Like Playing Styles Using Evolutionary Multi-Objective Deep Reinforcement Learning

no code implementations • 20 Oct 2019 • Ruimin Shen, Yan Zheng, Jianye Hao, Yinfeng Chen, Changjie Fan

this paper has been withdrawn

Efficient Two-Dimensional Sparse Coding Using Tensor-Linear Combination

no code implementations • 28 Mar 2017 • Fei Jiang, Xiao-Yang Liu, Hongtao Lu, Ruimin Shen

Sparse coding (SC) is an automatic feature extraction and selection technique that is widely used in unsupervised learning.

Denoising Vocal Bursts Valence Prediction

Graph Regularized Tensor Sparse Coding for Image Representation

no code implementations • 27 Mar 2017 • Fei Jiang, Xiao-Yang Liu, Hongtao Lu, Ruimin Shen

Sparse coding (SC) is an unsupervised learning scheme that has received an increasing amount of interests in recent years.

Clustering Image Clustering