New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Tval #14
Conversation
Codecov Report
@@ Coverage Diff @@
## master #14 +/- ##
==========================================
+ Coverage 47.05% 47.29% +0.23%
==========================================
Files 12 12
Lines 425 444 +19
==========================================
+ Hits 200 210 +10
- Misses 225 234 +9
Continue to review full report at Codecov.
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM. I just tested this with our use case again and it seems to do the job. I only get precision error gaps now which will be fixed by #12.
S = statetype(pomdp) | ||
O = obstype(pomdp) | ||
odict = Dict{O, Vector{Pair{Int, S}}}() | ||
|
||
if steps <= 0 | ||
return 0.0 | ||
return length(b.scenarios)*fval(pomdp, b) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Oh I see ... the reward here must be the sum over all scenarios... 👍
I figured it should probably not be called terminal_value because it is never called on terminal states, haha.