DeepGamingAI's video: Training AI Game Bots With Screen Pixels As Input To Level The Playing Field Game Futurology 12

This is episode of the video series "Game Futurology" covering the paper "CURL: Contrastive Unsupervised Representations for Reinforcement Learning" by Michael Laskin, Aravind Srinivas and Pieter Abbeel. PDF: https://arxiv.org/pdf/2004.04136.pdf Authors' Project Page: https://mishalaskin.github.io/curl/ Game Futurology: This is a video series consisting of short 2-3 minute overview of research papers in the field of AI and Game Development. This series aims to ponder over what the future games might look like based on the latest academic research going on in the field today. Subscribe for more weekly videos! Abstract: We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 2.8x and 1.6x performance gains respectively at the 100K interaction steps benchmark. On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency and performance of methods that use state-based features. Music Credits: https://www.fesliyanstudios.com/ ---------------------------------------------------------------- • YouTube - https://www.youtube.com/c/DeepGamingA... • Twitter - https://twitter.com/deepgamingai • Medium - https://medium.com/@chintan.t93 • GitHub - https://github.com/ChintanTrivedi --------------------------------------------------------------------