Benchmarking Unsupervised Representation Learning for Continuous Control | OpenReview

Benchmarking Unsupervised Representation Learning for Continuous Control May 29, 2020Submissionreaders: everyone Abstract: We address the problem of learning reusable state representations from a non-stationary stream of high-dimensional observations. This is important for areas that employ Reinforcement Learning (RL), which yields non-stationary data distributions during training. Unsupervised approaches can be trained on such data streams to produce low-dimensional latent embeddings, which

1 mentions: @_kainoa_
Date: 2020/06/29 18:52

Related Entries

Read more Deep Learning With Keras: Structured Time Series
0 users, 0 mentions 2018/10/15 03:14
Read more A Probabilistic U-Net for Segmentation of Ambiguous Images - YouTube
0 users, 1 mentions 2018/11/27 22:54
Read more GitHub - c-sommer/primitect: Code accompanying the paper "PrimiTect: Fast Continuous Hough Voting fo...
0 users, 0 mentions 2020/05/22 02:21
Read more [2001.00610] Representing Unordered Data Using Multiset Automata and Complex Numbersopen searchopen ...
0 users, 1 mentions 2020/06/01 15:51
Read more Efficient Data Annotation for Self-Driving Cars via Crowdsourcing on a Large-Scale
0 users, 0 mentions 2020/06/13 09:51