ML@Duke Seminar

Sponsor(s): Machine Learning, +DataScience (+DS), Bass Connections-Information, Society & Culture, Biomedical Engineering (BME), Biostatistics and Bioinformatics, Computational Biology and Bioinformatics (CBB), Computer Science, Electrical and Computer Engineering (ECE), Energy Initiative, Information Initiative at Duke (iiD), Information Science + Studies (ISS), Mathematics, Pratt School of Engineering, Social Science Research Institute (SSRI), and Statistical Science
Recurrent World Models Facilitate Policy Evolution
Abstract: We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own dream environment generated by its world model, and transfer this policy back into the actual environment.
Links:
https://worldmodels.github.io/
https://papers.nips.cc/paper/7512-recurrent-world-models-facilitate-policy-evolution
Contact: Ariel Dawn