Reinforcement learning for learning multi-step tasks on new objects in images
Reinforcement learning for learning multi-step tasks on new objects in images
Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks
arXiv paper abstract https://arxiv.org/abs/2109.10312
arXiv PDF paper https://arxiv.org/pdf/2109.10312.pdf
… study the problem of learning a repertoire of low-level skills from raw images that can be sequenced to complete long-horizon visuomotor tasks.
Reinforcement learning (RL) is a promising … However, … focus … on the success of those individual skills … more so than … extended multi-stage tasks.
… introduce EMBR, a model-based RL method for learning primitive skills that are suitable for completing long-horizon visuomotor tasks.
… model is task-agnostic and trained using data from all skills, enabling the robot to efficiently learn a number of distinct primitives.
These visuomotor primitive skills and their associated pre- and post-conditions can then be directly combined with off-the-shelf symbolic planners to complete long-horizon tasks.
… find that EMBR enables the robot to complete three long-horizon visuomotor tasks at 85% success rate, such as organizing an office desk, a file cabinet, and drawers, which require sequencing up to 12 skills, involve 14 unique learned primitives, and demand generalization to novel objects.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
