v0.2.0
PointBasedValueIteration v0.2.0
The new version updates the solver support for more than 2 state POMDPs.
The belief space expansion has been added as well.
Closed issues:
- Better to use reward(m, s, a, sp, o) and observation(m, s, a, sp) (#1)
- No need for
iterator
in requirements (#2) - Update badge location (#3)
Merged pull requests: