Thomas Knoll
|
604d2c2b76
|
changed action handling for probabilities
|
1 year ago |
|
Thomas Knoll
|
1528173f58
|
changed iterations to evaluations
|
1 year ago |
|
Thomas Knoll
|
d64f569499
|
commented out shield export call
|
1 year ago |
|
Thomas Knoll
|
b05029eff0
|
added init call
|
1 year ago |
|
Thomas Knoll
|
7a6496cfee
|
removed some type annotations in callback
|
1 year ago |
|
Thomas Knoll
|
f0df936716
|
added steps argument and stop criteria
|
1 year ago |
|
Thomas Knoll
|
b238f5c1a7
|
changed jupyter notebooks to tune
|
1 year ago |
|
Thomas Knoll
|
8650b7c91f
|
added tune example
changes to algorithm parsing
|
1 year ago |
|
Thomas Knoll
|
717c644aad
|
changed ray tune example
|
1 year ago |
|
Thomas Knoll
|
3dee543e24
|
renaming and notebooks
|
1 year ago |
|
Thomas Knoll
|
4e182a8e5b
|
removed basic training
|
1 year ago |
|
Thomas Knoll
|
138d917fd6
|
added tune example
refactored and evaluation logging
|
1 year ago |
|
Thomas Knoll
|
e2c855dc6a
|
added more shielding options
(training, evaluation, none, both)
|
1 year ago |
|
Thomas Knoll
|
f3747a1479
|
renaming / shield handling changes
|
1 year ago |
|
Thomas Knoll
|
757fbbcc0d
|
fixed shield generation
worker handling
|
1 year ago |
|
Thomas Knoll
|
1c2dbf706e
|
changed shield creation to create shield on reset
|
1 year ago |
|
Thomas Knoll
|
97f7d23cda
|
added rudimental key / door masking
|
1 year ago |
|
Thomas Knoll
|
b1b014dbd6
|
some refactoring as preparation for sb3 example
added sb3 example
|
1 year ago |
|
Thomas Knoll
|
fab1e8f23f
|
added logdir handling
chnages to action index handling
|
1 year ago |
|
Thomas Knoll
|
7f20c3f909
|
arguments and log dir
|
1 year ago |
|
Thomas Knoll
|
fe96a6a0b6
|
added dqn algorithm
|
1 year ago |
|
Thomas Knoll
|
e42becef88
|
added dqn handling skeleton
|
1 year ago |
|
Thomas Knoll
|
f52262ad11
|
simple masking (only turn left allowed)
|
1 year ago |
|
Thomas Knoll
|
cf18349819
|
basic action embedding
|
1 year ago |
