Koha9
1787872e82
wrong remain Time Fix
...
wrong remain Time Fix, what a stupid mistake...
and fix doubled WANDB writer
2022-12-04 09:20:05 +09:00
Koha9
ad9817e7a4
Totally disparate NN by target
...
Totally disparate NN by target.
2022-12-03 21:35:33 +09:00
Koha9
cbc385ca10
Change training dataset storage method
...
save training dataset by it target type.
while training NN use single target training set to backward NN.
this improve at least 20 times faster than last update!
2022-12-03 07:54:38 +09:00
Koha9
895cd5c118
Add EndReward Broadcast function
...
while game over add remaintime/15 to every step's rewards. to improve this round's training weight.
fix get target from states still using onehot decoder bug.
2022-12-03 03:58:19 +09:00
Koha9
3930bcd953
Add Multi-NN agent
...
Add Multi neural network in output layer
use different nn while facing to different target.
2022-12-01 19:55:51 +09:00
Koha9
5631569b31
Side Channel added
...
add side Channel to save target win ratio.
Fix some Bug
2022-11-30 06:45:07 +09:00
Koha9
32d398dbef
Change Learning timing
...
change learning timing to each episode end.
2022-11-16 19:40:57 +09:00
Koha9
a0895c7449
Add load & save function.
...
Add load & save function.
Add train flag to test model.
Add new action select function while in test mode.
Add decision period to skip step.
2022-11-08 23:14:34 +09:00
Koha9
474032d1e8
hybrid dis-con action, save-load, converge wad observed
...
add discrete and continuous action in same NN model.
model save and load.
reward is increasing, converge was observed.
this two models are seems good:
Aimbot_9331_1667423213_hybrid_train2
Aimbot_9331_1667389873_hybrid
2022-11-03 07:16:18 +09:00
Koha9
0dbe2013ae
weight and bias sync added
...
weight and bias sync added
2022-11-01 19:11:45 +09:00
Koha9
7497ffcb0f
Parallel Environment Discrete PPO finish
...
Parallel Environment Discrete PPO finish. Runnable.
2022-10-30 04:13:14 +09:00
Koha9
742529ccd7
Archive all tensorflow agents and env
...
archive all TF py&ipynb
turn face to pytorch.
2022-10-26 03:15:37 +09:00
Koha9
cf2e4cee2c
Unity Fix Timelimit UI didn't work
...
Unity Fix Timelimit UI didn't work
2022-10-24 00:14:06 +09:00
Koha9
818928a5aa
Add Gun State, fix PPO GAIL class bug
...
Add Gun state
fix PPO GAIL class errors
2022-10-23 23:38:07 +09:00
Koha9
6ab56880d8
GAIL class fix some bug, now runnable
...
GAIL class fix , no new function
2022-10-15 01:08:08 +09:00
Koha9
2a498f18f6
GAIL Class, human action record future added
...
add GAIL GAILMem GAILConfig Class.
add HumanAction record to save expert data.
add tackState future for stack multiple states to let agent knows what happened before.
2022-10-14 19:05:02 +09:00
Koha9
ae8a1ba8e2
Update PPO class,add python human control
...
Python:
Update PPO class
add python human control
Unity:
add FP/TP choose button
2022-10-11 06:40:15 +09:00
Koha9
de066f3a65
Delete near Enemy Detect future. Use different density sensor.
...
Unity:
No more detect Closest enemy info. Add different density sensor let agent get more state information on the center of view.
Adjust Start Scene UI manager. Add in game visible rayCast & information that rayCast detect.
Python:
Start use mypy black and flake8 to format Python.
2022-09-30 22:36:47 +09:00
Koha9
1aaf6c7069
Add Message Box & TimeLimit Change Button
...
Add Message Box & TimeLimit Change Button.
Start Using XXManager to keep script, now changed in UIManger GameObject.
2022-09-07 06:48:37 +09:00
Koha9
885dbb92e9
Add Enemy Change Button
...
Add Enemy Change Button. Tidy up Unity Script folder.
2022-09-06 23:01:55 +09:00
Koha9
0a07b03b7b
Fix python can't save score file issue
2022-09-05 21:39:17 +09:00
Koha9
8eb64fb75e
Unity repair LoadDir toggle too big issue
...
change loadDir toggle size to 20x20. delete toggle label.
2022-09-05 21:29:01 +09:00
Koha9
763d704efd
Add Save model weights immediately future
...
add save button@Unity then send "saveNow" Toggle to Python.
delete useless method "saveModel" and "loadModel". Use Save/load weights instead.
2022-09-05 21:22:34 +09:00
Koha9
2d404cfdf2
Aimbot Enviroment very first
...
Basic environment include Multi scene, Reward Change, Visible chart, etc....
2022-09-05 20:46:08 +09:00
Koha9
aa337c5fc2
Initial commit
2022-09-05 20:31:53 +09:00
Koha9