Novelty Search for Neuroevolution!
This video explains an algorithm achieving much better results on control tasks like Maze Navigation and Biped Locomotion by evaluating members in an evolutionary algorithm based on novelty rather than fitness! The paper link is in the description below, as well as a link to a previous video on the NEAT algorithm in which the novelty search objective is implemented on top of!
Thanks for watching! Please Subscribe!
Paper Link: https://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/lehman_ecj11.pdf
NEAT explained: https://www.youtube.com/watch?v=b3D8jPmcw-g&t=6s
Видео Novelty Search for Neuroevolution! канала Connor Shorten
Thanks for watching! Please Subscribe!
Paper Link: https://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/lehman_ecj11.pdf
NEAT explained: https://www.youtube.com/watch?v=b3D8jPmcw-g&t=6s
Видео Novelty Search for Neuroevolution! канала Connor Shorten
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Collaboration of ExpertsAI Weekly Update #12 - November 18th, 2019Healthsea from Spacy on HuggingFace SpacesDL Podcast #3 | Yannic Kilcher | Population-Based SearchDeep Learning Podcast #2 | Edward Peake | Deep Learning in Medical ImagingLong-Short TransformerKnowledge Distillation - Keras Code ExamplesApproximate Nearest Neighbor Benchmarks - Weaviate Podcast RecapBinary Passage Retrieval in Weaviate (32x Memory Savings)Beyond Goldfish Memory!AI Weekly Update 2.0Efficient Transfer Learning with Null PromptsGoogle Research at ICCVDeep Learning for Podcast Content Search (Summary of Interview with Alex Canan at Zencastr)Full Stack Neural SearchEvolving Normalization-Activation LayersCoDA: Contrast-Enhancing and Diversity-Promoting Data Augmentation for NLUHow recent papers from OpenAI may come togetherAI Weekly Update - March 15th, 20201 (#28)!MultiCite - New Research in Scientific Literature Mining!Self-Supervised GANs