update

Author: optimass

README.md

@@ -312,6 +312,10 @@ Learning MAML in a Meta continual learning way slows down forgetting
 
 ## Lifelong Reinforcement Learning
 - [**Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges**](http://www.sciencedirect.com/science/article/pii/S1566253519307377) , (2020) by *Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat and Natalia Díaz-Rodríguez* [[bib]](bibtex.bib#L1022-L1033) 
+- [**Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL**](https://openreview.net/forum?id=HyxAfnA5tm) , (2019) by *Anusha Nagabandi, Chelsea Finn and Sergey Levine* [[bib]](bibtex.bib#L630-L637) 
+``` 
+Formulates an online learning procedure that uses SGD to update model parameters, and an EM with a Chinese restaurant process prior to develop and maintain a mixture of models to handle non-stationary task distribution
+``` 
 - [**Experience replay for continual learning**](https://arxiv.org/abs/1811.11682) , (2019) by *Rolnick, David, Ahuja, Arun, Schwarz, Jonathan, Lillicrap, Timothy and Wayne, Gregory* [[bib]](bibtex.bib#L1162-L1170) 
 
 ## Continual Generative Modeling

bibtex.bib

@@ -627,13 +627,13 @@ @String(NIPS2019_9112=
 
 
 @inproceedings{
-nagabandi2018deep,
-title={Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL},
-author={Anusha Nagabandi and Chelsea Finn and Sergey Levine},
-booktitle={International Conference on Learning Representations},
-year={2019},
-url={https://openreview.net/forum?id=HyxAfnA5tm},
-    keywords={Continual-Meta Learning}
+        nagabandi2018deep,
+        title={Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL},
+        author={Anusha Nagabandi and Chelsea Finn and Sergey Levine},
+        booktitle={International Conference on Learning Representations},
+        year={2019},
+        url={https://openreview.net/forum?id=HyxAfnA5tm},
+        keywords={Continual-Meta Learning, Lifelong Reinforcement Learning}
 }
 @String(nagabandi2018deep="Formulates an online learning procedure that uses SGD to update model parameters, and an EM with a Chinese restaurant process prior to develop and maintain a mixture of models to handle non-stationary task distribution")