Udacity
This video is part of the Udacity course “Reinforcement Learning”. Watch the full course at https://www.udacity.com/course/ud600
Source
State Estimation Part Two
Similar Posts
Harry Potter wand teaches children to code
Awesome Video! Pretty Girl ChainSaw Top Big Tree Cutting Down Extreme Felling Wedge Fastest Skill
June TBR Viewers Choice. Enlightenment Now by Steven Pinker
One thought on “State Estimation Part Two”
Comments are closed.
Since POMDP specifies optimal action for every possible belief (where belief is distribution of probability over all states) it is as good as saying that it is an MDP with infinite states.