arXiv (Cornell University)· 2018· Preprint
Recurrent World Models Facilitate Policy Evolution
- 411citations
- 2018year
Short summary
A generative recurrent neural network trained unsupervisedly to model RL environments achieved state-of-the-art results when its extracted features were used to train compact policies via evolution.
AI-generated from the title and abstract; the full text is not read.
Key points
- Unsupervised training of a generative recurrent neural network to model RL environments.
- Extracted features from the world model enabled training of compact policies via evolution.
- Achieved state-of-the-art results in multiple RL environments.
- Demonstrated successful transfer of policies trained within a generated world model to the actual environment.
AI-generated from the title and abstract; the full text is not read.
Abstract
A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art results in various environments. We also train our agent entirely inside of an environment generated by its own internal world model, and transfer this policy back into the actual environment. Interactive version of paper at https://worldmodels.github.io
The authors' abstract, as published at the source. arXiv (Cornell University), 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Development
DevelopmentSocial Sciences