Learning Plannable Representations with Causal InfoGAN

Summary

This work by two students at UC Berkeley learns to navigate the environment without any objective function. The proposed model-based RL links observations and states in an unsupervised way, using the Infogan.

• Source code
• Read the paper

References

2. Learning Plannable Representations with Causal InfoGAN (2018)

   Kurutach, Thanard and Tamar, Aviv and Yang, Ge and Russell, Stuart and Abbeel, Pieter

4. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016)

   Chen, Xi and Duan, Yan and Houthooft, Rein and Schulman, John and Sutskever, Ilya and Abbeel, Pieter