Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control — mentioned by chronolitus

Wed, 26 May 2021 10:11:00 GMT

Consider this more a wild speculative rambling than actual thorough evaluation, so take that grain of salt (I do work in AI/vision research): The probability that they can safely pull this off is very low. Right now progress in vision-based ML is incredible. If you look at AK's twitter feed [1], you'll be amazed almost every day. But I work in planning, and for planning detecting / segmenting objects, even recreating 3d models is not enough, you need a full contextual model of the world. Right now, I have 0 clue how this could be done, I don't think anyone else does either. Here's an example…

Paper and discussion history. A mention is not an endorsement.

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control · HackerPapers discussions

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control — mentioned by chronolitus