Q-learning 走迷宮 | JavaScript 程式專案

{"id":59766,"student_id":10,"content":"// 一維迷宮\n// var grid = [\n//     '*******',\n//     '*    C*',\n//     '*******',\n// ];\n// 二維迷宮\n// var grid = [\n//     '******',\n//     '*    *',\n//     '* ** *',\n//     '* *C *',\n//     '*    *',\n//     '******',\n// ];\n// 隨機產生迷宮，如果遇到死路就再刷新一次！\nvar grid = randomGrid(16, 12, 0.3);\ninit(grid);\n\n// when('keyup', 'right', function () {\n//     player.x++;\n// });\n// when('keyup', 'left', function () {\n//     player.x--;\n// });\n\nplayer.reset(3, 1);\n\nvar Q = {}; //老鼠的大腦\nvar S1; //上一次的狀態(位置)\nvar S2; //當前的狀態(位置)\nvar A; //上一次的動作(移動方向)\nvar alpha = 0.8; // 學習速率\nvar beta = 0.5; // 衰減值\n\n\nforever(function(){\n    S1 = player.x + ':' + player.y;\n    if (Q[S1] == undefined) Q[S1] = [0, 0, 0, 0];\n    \n    // var max = Math.max(Q[S1][0], Q[S1][1], Q[S1][2], Q[S1][3]);\n    var max = Math.max(...Q[S1]); // 同上\n    var A = Q[S1].indexOf(max);\n    if (A == 0) player.x--;\n    if (A == 1) player.x++;\n    if (A == 2) player.y--;\n    if (A == 3) player.y++;\n    \n    S2 = player.x + ':' + player.y;\n    if (Q[S2] == undefined) Q[S2] = [0, 0, 0, 0];\n    \n    if (grid[player.y][player.x] == '*') { //撞到牆壁懲罰 -100\n        reword(Q, S1, A, S2, -100);\n        player.reset(1, 1);\n    }\n    if (grid[player.y][player.x] == 'C') { //找到起司獎勵 +10\n        reword(Q, S1, A, S2, 10);\n        player.reset(1, 1);\n    }\n    if (grid[player.y][player.x] == ' ') { //浪費步數懲罰 -1\n        reword(Q, S1, A, S2, -1);\n    }\n});\n\nfunction reword (Q, S1, A, S2, score) {\n    Q[S1][A] = alpha*Q[S1][A] + (1 - alpha)*(score + beta*Math.max(...Q[S2]));\n}","created_at":"2019-03-18T11:19:44.712+08:00","updated_at":"2019-11-11T16:25:08.477+08:00","name":"Q-learning 走迷宮","language":"javascript","screenshot":{"url":"https://cdn3.koding.school/uploads/project/screenshot/59766/8ed8401e8ae67e48c8684cfe08a91409.jpg"},"parent_id":3,"plugin":"var rat = createSprite('mouse.png');;\nvar cheese = createSprite('cheese.png');\nvar W;\nvar H;\nvar width = 40;\n\nfunction init (grid) {\n\n    H = grid.length;\n    W = grid[0].length;\n\n    for (var y = 0; y \u003c H; y++) {\n        for (var x = 0; x \u003c W; x++) {\n            if (grid[y][x] == 'C') {\n                cheese.moveTo(x*width + width/2, y*width + width/2);\n            }\n        }\n    }\n\n    forever(function() {\n        for (var y = 0; y \u003c H; y++) {\n            for (var x = 0; x \u003c W; x++) {\n                pen.fillColor = (grid[y][x] == '*' ? 'black' : 'white')\n                pen.drawRect(x*width, y*width, width, width);\n            }\n        }\n    });\n}\n\nfunction randomGrid (col, row, rate) {\n    var col = col \u003c 16 ? col : 16;\n    var row = row \u003c 12 ? row : 12;\n    var grid = [];\n    for (var y = 0; y \u003c row - 2; y++) {\n        grid[y] = '';\n        for (var x = 0; x \u003c col - 2 ; x++) {\n            if (x == col - 3 \u0026\u0026 y == row - 3) grid[y] += 'C';\n            else grid[y] += Math.random() \u003c rate ? '*' : ' ';\n        }\n        grid[y] = '*' + grid[y] + '*';\n    }\n    var s = Array(col).fill('*').join('');\n    grid.push(s);\n    grid.unshift(s);\n    return grid;\n}\n\nvar player = {\n    x: 1,\n    y: 1,\n    reset: function (x, y) {\n        this.x = x;\n        this.y = y;\n    }\n}\n\nforever(function () {\n    rat.moveTo(player.x*width + width/2, player.y*width + width/2);\n})\n\n","description":null,"note":null,"status":"public","like_student_ids":[],"is_featured":false,"views":341,"hashid":"d5ms63kw","is_content_changed":false,"review_status":"unsubmitted","submitted_at":null,"reviewed_at":null,"advise":null,"is_deleted":false}