发明专利
DE112020006045T5 FORMAL SICHERES SYMBOLISCHES BESTÄRKENDES LERNEN ANHAND VON VISUELLEN EINGABEN
未知
基本信息:
- 专利标题: FORMAL SICHERES SYMBOLISCHES BESTÄRKENDES LERNEN ANHAND VON VISUELLEN EINGABEN
- 申请号:DE112020006045 申请日:2020-12-07
- 公开(公告)号:DE112020006045T5 公开(公告)日:2022-10-06
- 发明人: DAS SUBHRO , HUNT NATHAN , FULTON NATHANIEL RYAN , HOANG TRONG NGHIA
- 申请人: IBM
- 专利权人: IBM
- 当前专利权人: IBM
- 优先权: US201916709633 2019-12-10
- 主分类号: G06V20/50
- IPC分类号: G06V20/50 ; G05D1/00 ; G06N20/00 ; G06V10/70
A method for training control software to reinforce safety constraints using visual inputs includes performing template matching for each object in an image of a reinforcement learning (RL) agent's action space using a visual template for each object wherein each object in the RL agent's action space is detected, mapping each detected object to a set of planar coordinates for each object in the RL agent's action space, determining a set of safe actions for the RL agent by applying a safety specification for the RL agent's action space to the set of variables for coordinates for each object in the RL agent's action space, outputting the set of safe actions to the RL agent for a current state of a RL procedure, and preventing the RL agent from executing an action that is unsafe, before the RL agent takes an action.