Chapter
Planning under uncertainty in belief space
21:36 - 31:44 (10:08)
In this podcast, the speaker discusses the concept of belief space and the problem of planning under uncertainty in real-world systems, where control is needed to manage beliefs in an uncertain environment.
Clips
The idea of optimality is shifting in the community, but the problem you have to solve is the problem you have to solve.
21:36 - 26:03 (04:27)
Summary
The idea of optimality is shifting in the community, but the problem you have to solve is the problem you have to solve. Planning under uncertainty is a difficult problem, but making approximations can lead to a computable solution.
ChapterPlanning under uncertainty in belief space
EpisodeLeslie Kaelbling: Reinforcement Learning, Planning, and Robotics
PodcastLex Fridman Podcast
The concept of belief space allows robots to not only consider the physical state of the world, but also their own beliefs about it and the potential outcomes of their actions.
26:03 - 29:24 (03:20)
Summary
The concept of belief space allows robots to not only consider the physical state of the world, but also their own beliefs about it and the potential outcomes of their actions. This approach opens up new possibilities for problem-solving and decision-making in robotics.
ChapterPlanning under uncertainty in belief space
EpisodeLeslie Kaelbling: Reinforcement Learning, Planning, and Robotics
PodcastLex Fridman Podcast
In this podcast episode, the speakers discuss the concept of abstraction and hierarchical planning in Artificial Intelligence.
29:24 - 31:44 (02:19)
Summary
In this podcast episode, the speakers discuss the concept of abstraction and hierarchical planning in Artificial Intelligence. They explain how building abstractions in the state space can help AI systems to make high-level plans and optimize the degree of uncertainty about the world.