snsd0805/Q-learning-in-C
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #1 from eeeXun/clang-format

Browse Source 
GitHub-Action auto format with clang-format
This commit is contained in:
Ting-Jun Wang 2023-05-31 16:45:50 +08:00 committed by GitHub
commit 5cf2ef7936
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 478 additions and 214 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

225
.clang-format Normal file
View File

@ -0,0 +1,225 @@
---
Language: Cpp
# BasedOnStyle: WebKit
AccessModifierOffset: -4
AlignAfterOpenBracket: DontAlign
AlignArrayOfStructures: None
AlignConsecutiveAssignments:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: true
AlignConsecutiveBitFields:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignConsecutiveDeclarations:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignConsecutiveMacros:
Enabled: false
AcrossEmptyLines: false
AcrossComments: false
AlignCompound: false
PadOperators: false
AlignEscapedNewlines: Right
AlignOperands: DontAlign
AlignTrailingComments:
Kind: Never
OverEmptyLines: 0
AllowAllArgumentsOnNextLine: true
AllowAllParametersOfDeclarationOnNextLine: true
AllowShortBlocksOnASingleLine: Empty
AllowShortCaseLabelsOnASingleLine: false
AllowShortEnumsOnASingleLine: true
AllowShortFunctionsOnASingleLine: All
AllowShortIfStatementsOnASingleLine: Never
AllowShortLambdasOnASingleLine: All
AllowShortLoopsOnASingleLine: false
AlwaysBreakAfterDefinitionReturnType: None
AlwaysBreakAfterReturnType: None
AlwaysBreakBeforeMultilineStrings: false
AlwaysBreakTemplateDeclarations: MultiLine
AttributeMacros:
- __capability
BinPackArguments: true
BinPackParameters: true
BitFieldColonSpacing: Both
BraceWrapping:
AfterCaseLabel: false
AfterClass: false
AfterControlStatement: Never
AfterEnum: false
AfterExternBlock: false
AfterFunction: true
AfterNamespace: false
AfterObjCDeclaration: false
AfterStruct: false
AfterUnion: false
BeforeCatch: false
BeforeElse: false
BeforeLambdaBody: false
BeforeWhile: false
IndentBraces: false
SplitEmptyFunction: true
SplitEmptyRecord: true
SplitEmptyNamespace: true
BreakAfterAttributes: Never
BreakAfterJavaFieldAnnotations: false
BreakArrays: true
BreakBeforeBinaryOperators: All
BreakBeforeConceptDeclarations: Always
BreakBeforeBraces: WebKit
BreakBeforeInlineASMColon: OnlyMultiline
BreakBeforeTernaryOperators: true
BreakConstructorInitializers: BeforeComma
BreakInheritanceList: BeforeColon
BreakStringLiterals: true
ColumnLimit: 0
CommentPragmas: '^ IWYU pragma:'
CompactNamespaces: false
ConstructorInitializerIndentWidth: 4
ContinuationIndentWidth: 4
Cpp11BracedListStyle: false
DerivePointerAlignment: false
DisableFormat: false
EmptyLineAfterAccessModifier: Never
EmptyLineBeforeAccessModifier: LogicalBlock
ExperimentalAutoDetectBinPacking: false
FixNamespaceComments: false
ForEachMacros:
- foreach
- Q_FOREACH
- BOOST_FOREACH
IfMacros:
- KJ_IF_MAYBE
IncludeBlocks: Preserve
IncludeCategories:
- Regex: '^"(llvm|llvm-c|clang|clang-c)/'
Priority: 2
SortPriority: 0
CaseSensitive: false
- Regex: '^(<|"(gtest|gmock|isl|json)/)'
Priority: 3
SortPriority: 0
CaseSensitive: false
- Regex: '.*'
Priority: 1
SortPriority: 0
CaseSensitive: false
IncludeIsMainRegex: '(Test)?$'
IncludeIsMainSourceRegex: ''
IndentAccessModifiers: false
IndentCaseBlocks: false
IndentCaseLabels: false
IndentExternBlock: AfterExternBlock
IndentGotoLabels: true
IndentPPDirectives: None
IndentRequiresClause: true
IndentWidth: 4
IndentWrappedFunctionNames: false
InsertBraces: false
InsertNewlineAtEOF: false
InsertTrailingCommas: None
IntegerLiteralSeparator:
Binary: 0
BinaryMinDigits: 0
Decimal: 0
DecimalMinDigits: 0
Hex: 0
HexMinDigits: 0
JavaScriptQuotes: Leave
JavaScriptWrapImports: true
KeepEmptyLinesAtTheStartOfBlocks: true
LambdaBodyIndentation: Signature
LineEnding: DeriveLF
MacroBlockBegin: ''
MacroBlockEnd: ''
MaxEmptyLinesToKeep: 1
NamespaceIndentation: Inner
ObjCBinPackProtocolList: Auto
ObjCBlockIndentWidth: 4
ObjCBreakBeforeNestedBlockParam: true
ObjCSpaceAfterProperty: true
ObjCSpaceBeforeProtocolList: true
PackConstructorInitializers: BinPack
PenaltyBreakAssignment: 2
PenaltyBreakBeforeFirstCallParameter: 19
PenaltyBreakComment: 300
PenaltyBreakFirstLessLess: 120
PenaltyBreakOpenParenthesis: 0
PenaltyBreakString: 1000
PenaltyBreakTemplateDeclaration: 10
PenaltyExcessCharacter: 1000000
PenaltyIndentedWhitespace: 0
PenaltyReturnTypeOnItsOwnLine: 60
PointerAlignment: Left
PPIndentWidth: -1
QualifierAlignment: Leave
ReferenceAlignment: Pointer
ReflowComments: true
RemoveBracesLLVM: false
RemoveSemicolon: false
RequiresClausePosition: OwnLine
RequiresExpressionIndentation: OuterScope
SeparateDefinitionBlocks: Leave
ShortNamespaceLines: 1
SortIncludes: CaseSensitive
SortJavaStaticImport: Before
SortUsingDeclarations: LexicographicNumeric
SpaceAfterCStyleCast: false
SpaceAfterLogicalNot: false
SpaceAfterTemplateKeyword: true
SpaceAroundPointerQualifiers: Default
SpaceBeforeAssignmentOperators: true
SpaceBeforeCaseColon: false
SpaceBeforeCpp11BracedList: true
SpaceBeforeCtorInitializerColon: true
SpaceBeforeInheritanceColon: true
SpaceBeforeParens: ControlStatements
SpaceBeforeParensOptions:
AfterControlStatements: true
AfterForeachMacros: true
AfterFunctionDefinitionName: false
AfterFunctionDeclarationName: false
AfterIfMacros: true
AfterOverloadedOperator: false
AfterRequiresInClause: false
AfterRequiresInExpression: false
BeforeNonEmptyParentheses: false
SpaceBeforeRangeBasedForLoopColon: true
SpaceBeforeSquareBrackets: false
SpaceInEmptyBlock: true
SpaceInEmptyParentheses: false
SpacesBeforeTrailingComments: 1
SpacesInAngles: Never
SpacesInConditionalStatement: false
SpacesInContainerLiterals: true
SpacesInCStyleCastParentheses: false
SpacesInLineCommentPrefix:
Minimum: 1
Maximum: -1
SpacesInParentheses: false
SpacesInSquareBrackets: false
Standard: Latest
StatementAttributeLikeMacros:
- Q_EMIT
StatementMacros:
- Q_UNUSED
- QT_REQUIRE_VERSION
TabWidth: 8
UseTab: Never
WhitespaceSensitiveMacros:
- BOOST_PP_STRINGIZE
- CF_SWIFT_NAME
- NS_SWIFT_NAME
- PP_STRINGIZE
- STRINGIZE
...

26
.github/workflows/format.yml vendored Normal file
View File

@ -0,0 +1,26 @@
name: format
on:
push:
branches:
- master
paths:
- "**.c"
- "**.h"
jobs:
format:
runs-on: ubuntu-latest
permissions:
contents: write
steps:
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
- name: Install clang-format
run: pip install clang-format
- name: Format with clang-format
run: clang-format -i *.c *.h
- name: Commit changes
uses: stefanzweifel/git-auto-commit-action@v4
with:
commit_message: "style(format): run clang-format"

37
enviroment.c
View File

@ -1,8 +1,8 @@
#include <stdio.h>
#include <math.h>
#include <assert.h>
#include "constant.h"
#include "enviroment.h" #include "enviroment.h"
#include "constant.h"
#include <assert.h>
#include <math.h>
#include <stdio.h>
short PATHS[8][3] = { short PATHS[8][3] = {
{ 0, 1, 2 }, { 3, 4, 5 }, { 6, 7, 8 }, { 0, 1, 2 }, { 3, 4, 5 }, { 6, 7, 8 },
@ -19,7 +19,8 @@ short PATHS[8][3] = {
Results: Results:
- None, set all blocks on the chessboard to zero. - None, set all blocks on the chessboard to zero.
*/ */
void reset(short* board){ void reset(short* board)
{
for (short i = 0; i < 9; i++) for (short i = 0; i < 9; i++)
board[i] = 0; board[i] = 0;
} }
@ -33,7 +34,8 @@ void reset(short* board){
Results: Results:
- None. Only printing. - None. Only printing.
*/ */
void show(short *board){ void show(short* board)
{
short loc; short loc;
printf("┼───┼───┼───┼\n"); printf("┼───┼───┼───┼\n");
for (short i = 0; i < 3; i++) { for (short i = 0; i < 3; i++) {
@ -64,7 +66,8 @@ void show(short *board){
Results: Results:
- None. All available actions are saved into "result" and the number of actions is saved in "length" - None. All available actions are saved into "result" and the number of actions is saved in "length"
*/ */
void get_available_actions(short *board, short *result, short *length){ void get_available_actions(short* board, short* result, short* length)
{
short index = 0; short index = 0;
for (int i = 0; i < 9; i++) for (int i = 0; i < 9; i++)
if (board[i] == 0) if (board[i] == 0)
@ -81,10 +84,13 @@ void get_available_actions(short *board, short *result, short *length){
Results: Results:
- short winner_number(integer): winner's number, 0 for no winner now, 1 for Bot, 2 for opponent - short winner_number(integer): winner's number, 0 for no winner now, 1 for Bot, 2 for opponent
*/ */
short get_winner(short *board){ short get_winner(short* board)
{
int a, b, c; int a, b, c;
for (int i = 0; i < 8; i++) { for (int i = 0; i < 8; i++) {
a = PATHS[i][0]; b = PATHS[i][1]; c = PATHS[i][2]; a = PATHS[i][0];
b = PATHS[i][1];
c = PATHS[i][2];
if ((board[a] == board[b]) && (board[b] == board[c]) && (board[a] != 0)) { if ((board[a] == board[b]) && (board[b] == board[c]) && (board[a] != 0)) {
return board[a]; return board[a];
} }
@ -101,7 +107,8 @@ short get_winner(short *board){
Results: Results:
- int hash (integer): chessboard's status in i-th block * pow(3, i) - int hash (integer): chessboard's status in i-th block * pow(3, i)
*/ */
int state_hash(short *board){ int state_hash(short* board)
{
int base, hash = 0; int base, hash = 0;
for (int i = 0; i < 9; i++) { for (int i = 0; i < 9; i++) {
base = pow(3, i); base = pow(3, i);
@ -110,7 +117,6 @@ int state_hash(short *board){
return hash; return hash;
} }
/* /*
Act on the chessboard. Act on the chessboard.
@ -125,7 +131,8 @@ int state_hash(short *board){
Results: Results:
- None. Save in state & reward & winner - None. Save in state & reward & winner
*/ */
void act(short *board, struct action *a, int *state, float *reward, float *opponent_reward, short *winner){ void act(short* board, struct action* a, int* state, float* reward, float* opponent_reward, short* winner)
{
// printf("Act( player=%d, action=%d )\n", a->player, a->loc); // printf("Act( player=%d, action=%d )\n", a->player, a->loc);
assert(board[a->loc] == 0); assert(board[a->loc] == 0);
board[a->loc] = a->player; board[a->loc] = a->player;
@ -134,12 +141,10 @@ void act(short *board, struct action *a, int *state, float *reward, float *oppon
if (*winner == a->player) { if (*winner == a->player) {
*reward = 1.0; *reward = 1.0;
*opponent_reward = -1.0; *opponent_reward = -1.0;
} } else if (*winner != 0) {
else if(*winner != 0){
*reward = -1.0; *reward = -1.0;
*opponent_reward = 1.0; *opponent_reward = 1.0;
} } else {
else{
*reward = 0; *reward = 0;
*opponent_reward = 0; *opponent_reward = 0;
} }

11
main.c
View File

@ -1,12 +1,13 @@
#include <stdio.h>
#include <time.h>
#include <stdlib.h>
#include <stdbool.h>
#include "constant.h" #include "constant.h"
#include "enviroment.h" #include "enviroment.h"
#include "q-learning.h" #include "q-learning.h"
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
int main(){ int main()
{
short board[9] = { 0 }; // tic tac toe's chessboard short board[9] = { 0 }; // tic tac toe's chessboard
float table[STATE_NUM][ACTION_NUM]; // q-learning table float table[STATE_NUM][ACTION_NUM]; // q-learning table

29
q-learning.c
View File

@ -1,7 +1,7 @@
#include <stdio.h>
#include <float.h> #include <float.h>
#include <stdbool.h>
#include <limits.h> #include <limits.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h> #include <stdlib.h>
#include "constant.h" #include "constant.h"
@ -17,7 +17,8 @@
Results: Results:
- short index (integer): the index with the max value - short index (integer): the index with the max value
*/ */
short float_argmax(float *arr, short length){ short float_argmax(float* arr, short length)
{
float ans = -1, max = -FLT_MAX; float ans = -1, max = -FLT_MAX;
for (short i = 0; i < length; i++) { for (short i = 0; i < length; i++) {
if (arr[i] > max) { if (arr[i] > max) {
@ -28,7 +29,6 @@ short float_argmax(float *arr, short length){
return ans; return ans;
} }
/* /*
Choose the next action with Epsilon-Greedy. Choose the next action with Epsilon-Greedy.
EPSILON means the probability to choose the best action in this state from Q-Table. EPSILON means the probability to choose the best action in this state from Q-Table.
@ -42,7 +42,8 @@ short float_argmax(float *arr, short length){
Results: Results:
- short best_choice - short best_choice
*/ */
short bot_choose_action(float *table, short *board, int state){ short bot_choose_action(float* table, short* board, int state)
{
// get available actions for choosing // get available actions for choosing
short available_actions[9]; short available_actions[9];
@ -90,7 +91,8 @@ short bot_choose_action(float *table, short *board, int state){
Results: Results:
- short choice (integer): random, -1 means no available action to choose - short choice (integer): random, -1 means no available action to choose
*/ */
short opponent_random_action(float *table, short *board, int state){ short opponent_random_action(float* table, short* board, int state)
{
// get available actions for choosing // get available actions for choosing
short available_actions[9]; short available_actions[9];
@ -118,7 +120,8 @@ short opponent_random_action(float *table, short *board, int state){
Results: Results:
- None. - None.
*/ */
void init_table(float *table){ void init_table(float* table)
{
for (int i = 0; i < STATE_NUM; i++) { for (int i = 0; i < STATE_NUM; i++) {
for (int j = 0; j < ACTION_NUM; j++) { for (int j = 0; j < ACTION_NUM; j++) {
*(table + i * ACTION_NUM + j) = 0; *(table + i * ACTION_NUM + j) = 0;
@ -137,7 +140,8 @@ void init_table(float *table){
Results: Results:
- int max_reward - int max_reward
*/ */
float get_estimate_reward(float *table, short *board, int state){ float get_estimate_reward(float* table, short* board, int state)
{
short available_actions[9]; short available_actions[9];
short available_action_length; short available_action_length;
get_available_actions(board, available_actions, &available_action_length); get_available_actions(board, available_actions, &available_action_length);
@ -165,7 +169,8 @@ float get_estimate_reward(float *table, short *board, int state){
Results: Results:
- None - None
*/ */
void run(float *table, short *board, bool train, int times, bool plot){ void run(float* table, short* board, bool train, int times, bool plot)
{
short available_actions[9]; short available_actions[9];
short available_actions_length; short available_actions_length;
short winner; short winner;
@ -187,7 +192,8 @@ void run(float *table, short *board, bool train, int times, bool plot){
estimate_r = *(table + state * ACTION_NUM + choice); estimate_r = *(table + state * ACTION_NUM + choice);
act(board, &a, &_state, &r, &opponent_r, &winner); act(board, &a, &_state, &r, &opponent_r, &winner);
if (plot) show(board); if (plot)
show(board);
// opponent random // opponent random
if (winner == 0) { if (winner == 0) {
@ -196,7 +202,8 @@ void run(float *table, short *board, bool train, int times, bool plot){
a.loc = opponent_choice; a.loc = opponent_choice;
a.player = OPPONENT_SYMBOL; a.player = OPPONENT_SYMBOL;
act(board, &a, &_state, &opponent_r, &r, &winner); act(board, &a, &_state, &opponent_r, &r, &winner);
if (plot) show(board); if (plot)
show(board);
} }
} }
get_available_actions(board, available_actions, &available_actions_length); get_available_actions(board, available_actions, &available_actions_length);