eabbb656cb
V3.4 追加Save Model按钮
...
追加Save Model按钮，对应按钮按下时显示message修改了font
2023-10-12 22:48:02 +09:00
5365c0749f
V3.3.9 LevelProbabilityPanel追加对Inputfiled支持
...
LevelProbabilityPanel追加对Inputfiled支持
2023-10-11 03:10:21 +09:00
1b48950e91
V3.3.8 追加Attack SceneLevel
...
追加Attack SceneLevel
2023-10-10 04:51:58 +09:00
9219b3d0da
V3.3.7 转移SceneBlockPrefabSet
...
转移SceneBlockPrefabSet至Scene Start的StartSceneData中
2023-10-08 23:56:11 +09:00
86e51f849f
V3.3.6 LevelProbabilityPanel 逻辑错误修正
2023-10-08 03:05:54 +09:00
0b23c91832
V3.3.5 LevelProbabilityPanel逻辑完成
2023-10-05 23:49:34 +09:00
19761315f2
V3.3.4 LevelProbabilityPanel大于0判断逻辑修复
...
LevelProbabilityPanel大于0判断逻辑修复
2023-10-05 22:56:09 +09:00
198ecff461
V3.3.3 LevelProbabilityPanel联动完成
...
添加限制总值小于1，最低值大于0限制
2023-10-05 18:29:43 +09:00
ae48180b8d
V3.3.2 LevelProbabilityPanel初始化完成
...
LevelProbabilityPanel初始化完成
独立Target enum类
2023-09-14 20:13:53 +09:00
904dc81c12
start画面button颜色动画添加
...
start画面button颜色动画添加
button颜色Changer修改为通用。
2023-09-09 21:04:57 +09:00
6dffd4185d
V3.3.1 添加一些summary
...
添加一些summary
2023-09-08 22:05:43 +09:00
203407693c
V3.3.0 MultiLevel功能创建完成
...
MultiLevel功能创建完成，play模式基本功能适配结束。下次再也不隔这么久commit一次了:(
2023-09-08 07:15:49 +09:00
5226f1dbbf
V3.2.2 开始创建MultiLevel
...
使用Multi level使AI适应更复杂环境
基本Level创建完成
UI逻辑创建中
2023-08-23 02:58:50 +09:00
3381c83604
V3.2.1 向InGameMessageBox添加颜色功能 整理代码
...
V3.2.1 向InGameMessageBox添加颜色功能 整理代码
2023-08-15 19:47:14 +09:00
709f7cf9d3
V3.2.0 添加InGameMessageBox 修改Playmode中小错误
...
添加InGameMessageBox，可以在游戏中显示某些消息
修正可以在Enemy或者Agent身上生成Target或者Enemy的错误
2023-08-09 01:28:09 +09:00
4318803f85
V3.1.7 修正ChartOn不工作问题
...
V3.1.7 修正ChartOn不工作问题
2023-08-08 16:34:46 +09:00
df1958c48e
V3.1.6 修正TrainMode中Target不更新问题
...
修正TrainMode中Target不更新问题
2023-07-29 04:04:18 +09:00
630cbc4f70
V3.1.5 修正PlayMode中TargetUI问题
...
修正TargetUI初始化StayMode Button可使用的问题
修正TargetUI可使用按钮逻辑问题
修正TargetUI与TargetController联动问题
修正Enemy击杀后不死亡问题
2023-07-28 19:44:02 +09:00
13e5c82862
V3.1.4 应用Parameter数值到Script
...
应用Parameter数值到Script
2023-07-11 18:32:28 +08:00
0b0c0771ce
V3.1.3 优化代码
...
分离AgentController和MLAgentsController
2023-07-10 01:51:44 +08:00
246ac4adfa
V3.1.2 追加Train Button选择
...
引入DOTween Plugin
追加Train Button选择和其动画
优化代码
2023-07-08 22:22:31 +08:00
cfccd12820
V3.1.1 优化代码
...
优化可读性与规范化命名方式
2023-06-30 18:30:12 +09:00
64e477d6c2
V3.1 控制模式完成
...
完成控制模式中UI，解决所有逻辑问题。控制模式于Unity中正常运行，可正常判断结束。
2023-06-29 15:18:10 +09:00
ff094aaba5
V3.0 追加控制模式，改进代码
...
追加控制模式，实现鼠标在地图中的坐标映射
追加控制UI
Todo：
游戏流程修改
游戏State对应修改
2023-04-09 23:35:38 +09:00
71f2687422
V2.9 取消归一化，追加StateUI，改进代码
...
取消坐标归一化，朝向归一化算法改为transform.eulerAngles.y / 36f
2023-03-07 17:29:47 +09:00
faa4e7b065
V2.8 移动算法更新
...
过去X与Y可同时达到maxspeed致使速度会超过maxspeed，本次修正了该错误。
追加移动Penalty。
2023-02-15 21:07:10 +09:00
5ccb06c545
V2.7 Normalized state
...
Normalized distance and rotation state.
2022-12-18 20:17:17 +09:00
64ada808de
V2.6 change Ray Tag result as Onehot
...
change Ray Tag result as Onehot,
Observation State:
-targetStates 6
-inTargetArea 1
-remainTime 1
-gunReady 1
-my Obs 4
-tag onehot 19*2
-tag dis 19
2022-12-10 10:14:44 +09:00
9b2ba7fb46
V2.5 Change reward function
...
Add chart Toggle to turn on reward chart real time in game.
Add enemy num changer, now can change enemy num in game.
Change facing to enemy reward function, while facing center line far from enemy will not get reward any more.
2022-12-10 09:11:42 +09:00
f9b806de02
V2.4 Add new reward function
...
add new reward function in attack mode
calculate distance between closest enemy and facing center line.
let agent could spawn in whole map area.
add penalty while mouseX is moving.
2022-12-08 06:27:49 +09:00
b2f80287d5
V2.3 Change State order
...
Change State order as
target state x6
in area state x1
remain time x1
gun state x1
my state x4
ray state ...
2022-12-08 06:27:49 +09:00
a0563646e3
V2.2 Fix Rotation State error
...
Fix Rotation State not unique error
2022-12-08 06:27:49 +09:00
74c85c4296
V2.1 Easier game!
...
Build-ParallelEnv-Target-OffPolicy-SingleStack-SideChannel-EndReward-Easy-V2.1
move remain time position after target state
easier game reward get, while watching or shoot at target area u get reward(attack mode), watching enemy u also get reward(Freemode)
2022-12-08 06:27:49 +09:00
fa90ac3bb6
V2.1 Add spin penalty and reward adjust
...
Build-ParallelEnv-Target-OffPolicy-SingleStack-SideChannel-EndReward-Easy-V2.1
add spin penalty while agent keep spin will give a penalty reward.
lower Go target in area reward.
2022-12-08 06:27:49 +09:00
0d60c857b7
V2.0 Bug Fix, scene added
...
fix scene only spawn in a small area in center.
delete room type attack target.
make no more enemy spawn in go target.
free mode enemy number change to 3.
2022-12-08 06:27:49 +09:00
8570a5ba5e
bug fix
...
fix target attack always win in first round.
2022-12-01 19:52:52 +09:00
9585845ba2
Side channel Added
...
add side channel to let python side know which target got win or lose.
fix update time bug. may cause double gameover check.(got another lose after reset the game.)
2022-11-30 06:39:56 +09:00
25eac00c53
Target & dynamic reward System V1.0
...
太多了...总之能用了，就这样吧，也懒得用英文写了(;´Д`)
ParameterContainer用于管理所有的Reward和Parameter.
TargetController用于生成目标，然后再让SceneBlockContainer实际生成目标块，并且兼顾reward计算功能和目标观察结果的获取.
EnemyContainer用于生成和删除敌人.
SceneBlockContainer用于生成和删除目标块.
States用于管理HP.
SceneBlock用于管理目标块的...一堆东西，比如目标大小，目标区内人数等和目标所属状态等.
2022-11-29 07:54:08 +09:00
6e32da8b64
Add ParameterContainer
...
Add Parameter Container. make environment parameter adjustment easier.
2022-11-08 00:58:47 +09:00
b53612d3c6
In-game real time reward chart, free camera, result viewer and etc...
...
In-game real time reward chart,
result viewer,
free camera,
kill bonus reward(not so good. set 0 to unuse it)
Fix ray-sensor throw error when initialization issue.
Fix ray-sensor info panel face to wrong position.
2022-11-03 07:10:00 +09:00
ad547e4edb
Parallel environment.
...
delete all unuse feature for Parallel environment.
it's possible to run each single environment independent
2022-10-26 16:20:27 +09:00
6bc1456e4b
Fist Sub
...
based on aimbot multi seane
2022-10-26 04:07:39 +09:00
1fbaf9d540
Initial commit
2022-10-26 04:06:44 +09:00
