 sp
|
71854bae01
|
init evalCallback for training with sb3
|
11 months ago |
|
sp
|
59c795348e
|
changes in sb3 rl training
- included callbacks for initial image and info plotting
- switched to CnnPolicy
- changed GRID_TO_PRISM_BINARY to environment var M2P_BINARY
|
11 months ago |
|
sp
|
315b0c8e7d
|
added useful sb3 callbacks
|
11 months ago |
|
sp
|
62c1198f25
|
removed observation changes from shielding wrapper
|
11 months ago |
|
sp
|
16490a74f1
|
init Miniwrapper to switch to WxHxC observations
|
11 months ago |
|
sp
|
7ccbe8f9bc
|
changes according to refactoring of utils
|
11 months ago |
|
sp
|
372006a1da
|
major refactor in utils
- introduced common_parser for arguments
- the shield dict uses minigrid.core.State instead of strings
- switched shield query to minigrid get_symbolic_state
|
11 months ago |
 Thomas Knoll
|
175171c035
|
added jpg remove on gif create
|
11 months ago |
|
sp
|
521c71eba4
|
removed erroneous file write
|
11 months ago |
|
sp
|
4486dba2c9
|
disabled shield creation at reset WIP
|
11 months ago |
|
sp
|
aa2cec0e0f
|
disabled default shield creation on reset
|
11 months ago |
|
sp
|
7eeb816013
|
changed default env
|
11 months ago |
|
sp
|
c7c2296c71
|
changed early stopping criterion in tuner
|
11 months ago |
|
Thomas Knoll
|
555511bd34
|
args for turn prob
|
11 months ago |
|
Thomas Knoll
|
f8a3c52b9c
|
fixed shielding
|
11 months ago |
|
Thomas Knoll
|
1cbaac75cb
|
cleanups
|
11 months ago |
|
Thomas Knoll
|
5dcabef8e0
|
added utils classes
|
11 months ago |
|
Thomas Knoll
|
ae94b57876
|
changed iteration handling
|
11 months ago |
|
Stefan Pranger
|
f3b12f4caa
|
removed callbacks for shield info
|
11 months ago |
|
sp
|
dd8809b517
|
trying add_text
|
11 months ago |
|
sp
|
8d7546cfc7
|
trying subdirectory
|
11 months ago |
|
sp
|
d4cc2aa3b9
|
debugging
|
11 months ago |
|
sp
|
7cc0f5984a
|
debugging
|
11 months ago |
|
sp
|
ac1bddc1ec
|
flush after writing text
|
11 months ago |
|
sp
|
1d6b12ba5a
|
fixed typo
|
11 months ago |
|
sp
|
e8dc44673d
|
another try
|
11 months ago |
|
sp
|
8599241c01
|
set file_writer as field
|
11 months ago |
|
sp
|
24badd36ac
|
trying to log on every episode start
|
11 months ago |
|
sp
|
68ce459756
|
fixed typo
|
11 months ago |
|
sp
|
f35083e669
|
callback on algo init
|
11 months ago |
|
sp
|
de5f35dd5f
|
moved text writing to standard callback
|
11 months ago |
|
sp
|
bbca8bd372
|
fixed include
|
11 months ago |
|
sp
|
adfb4034ce
|
make multi callbacks
|
11 months ago |
|
sp
|
fd08a1f36e
|
passing multiple callbacks as list
|
11 months ago |
|
sp
|
07841090c6
|
sh info callback, removed ws
|
11 months ago |
|
sp
|
0f3af93c68
|
fixed include
|
11 months ago |
|
sp
|
cc39cca0ab
|
fixed typo, removed ws
|
11 months ago |
|
sp
|
618ab6e73c
|
added num_gpus as arg, first try sh info callback
|
11 months ago |
|
Thomas Knoll
|
7ec988da12
|
log dir change
|
11 months ago |
|
Thomas Knoll
|
45d110b199
|
added probability arguments
|
12 months ago |
|
Thomas Knoll
|
af0c4e2f21
|
shield value script 15
|
12 months ago |
|
Thomas Knoll
|
5c9064ecbe
|
randomize start
|
12 months ago |
|
Thomas Knoll
|
80cbbe5a3a
|
minor changes
|
12 months ago |
Thomas Knoll
|
71acf4e2cc
|
added checkpoint & sandbox
|
1 year ago |
|
Thomas Knoll
|
afc9f5bc4d
|
added config / some adversary fixes
|
1 year ago |
|
Thomas Knoll
|
5745113179
|
changed one hot wrapping
|
1 year ago |
|
Thomas Knoll
|
d41ba6258f
|
adversary handling
|
1 year ago |
|
Thomas Knoll
|
906f251401
|
some fixes to key and door handling
|
1 year ago |
|
Thomas Knoll
|
ddc0a048b2
|
more args and door / key handling
|
1 year ago |
|
Thomas Knoll
|
bd09223fad
|
added shieldhandler key handling
|
1 year ago |
