google-deepmind / google-deepmind/dm_control
Rendering the viewer with substeps (aka. physical timestep) instead of steps (aka. control timestep)
未关闭
- 主要语言
- Python
- 星标
- 4.7k
- 派生
- 764
- PR 合并指标
- 30 天内没有已合并 PR
描述
I made my own task in dm_control, but unfortunately, the action of my task is not only the actuator control values but also an unfixed control duration. For every control step, my agent will decide how long this control period is, and the time vary from 0.02 to 0.1 seconds (the details are just setting the timestep before every step).
I would like to render my dm_control env under the 'viewer' module your package provided.
How can I implement it in this situation?
贡献指南
调研方向
首先定位 viewer 模块,并阅读它如何相对于控制步推进仿真时间。确定可变控制时长和物理子步是如何表示的;当控制步之间的时长发生变化时,viewer 能够正确渲染此环境即表示完成。
由索引模型根据 Issue 内容生成。
评估
- 技术栈
- python
- 领域
- computer-graphics
- Issue 类型
- 功能
- 难度
- 5/5
- 预计耗时
- 一周以上
- 活跃度
- 停滞
- 描述清晰度
- 需要澄清
- 新手友好度
- 20/100