Q-learning | JavaScript Programming Project | OrangeApple Learning Platform

{"id":28969,"student_id":10,"content":"var btn1 = createSprite(\"btn.png\");\nbtn1.x = 50;\nbtn1.y = 100;\nbtn1.scale = 0.3;\nbtn1.disable = false;\n\nvar btn2 = createSprite(\"btn.png\");\nbtn2.x = 50;\nbtn2.y = 200;\nbtn2.scale = 0.3;\nbtn2.disable = true;\n\nvar btn3 = createSprite(\"btn.png\");\nbtn3.x = 50;\nbtn3.y = 300;\nbtn3.scale = 0.3;\nbtn3.disable = true;\n\nvar btn4 = createSprite(\"btn.png\");\nbtn4.x = 50;\nbtn4.y = 400;\nbtn4.scale = 0.3;\n\nbtn1.on(\"click\", move);\nbtn2.on(\"click\", calc);\nbtn3.on(\"click\", update);\nbtn4.on(\"click\", () =\u003e sw = !sw);\n\nvar map = [\n    [1, 1, 1, 1, 1, 1],\n    [1, 0, 0, 0, 0, 1],\n    [1, 0, 0, 1, 0, 1],\n    [1, 0, 1, 2, 0, 1],\n    [1, 0, 0, 0, 0, 1],\n    [1, 1, 1, 1, 1, 1]\n];\n\nvar Q = {};\nfor (var x = 0; x \u003c 10; x++) {\n    for (var y = 0; y \u003c 10; y++) {\n        Q[x+':'+y] = [0, 0, 0, 0];\n    }\n}\n\nvar w = 70;\nvar player = { x: 1, y: 1 };\nvar sw = 0;\nvar S = '1:1';\nvar A;\nvar _S;\nvar alpha = 0.5;\nvar beta = 0.1;\nvar re = '';\nvar formula = '';\n\nvar clock = 0;\nsetInterval(function() {\n    clock++;\n    if (sw) {\n        if (clock%3 == 0) move();\n        if (clock%3 == 1) calc();\n        if (clock%3 == 2) update();\n    }\n}, 30);\n\n\nfunction move () {\n    if (btn1.disable) return;\n    \n    var block = map[player.y][player.x];\n    S = player.x + ':' + player.y;\n\n    if (block == 1 || block == 2) {\n        player.x = 1;\n        player.y = 1;\n    } else {\n        A = Q[S].indexOf(Math.max(...Q[S]));\n        if (A == 3) player.y -= 1; // 上\n        if (A == 2) player.x += 1; // 右\n        if (A == 1) player.y += 1; // 下\n        if (A == 0) player.x -= 1; // 左\n        btn1.disable = true;\n        btn2.disable = false;\n    }\n}\n\nfunction calc () {\n    if (btn2.disable) return;\n\n    var block = map[player.y][player.x];\n    _S = player.x + ':' + player.y;\n    if (block == 0) re = reward(S, A, -10,  _S); // 白色\n    if (block == 1) re = reward(S, A, -100, _S); // 黑洞\n    if (block == 2) re = reward(S, A, +500, _S); // 寶藏\n    \n    var r = block == 0 ? '-10' : block == 1 ? '-100' : '+500';\n    formula = `Q[${S}] = (${Q[S][A]} + (${r} + Max([${Q[_S].toString()}])*0.1)/2`\n    \n    btn2.disable = true;\n    btn3.disable = false;\n}\n\nfunction update () {\n    if (btn3.disable) return;\n\n    Q[S][A] = re;\n    btn3.disable = true;\n    btn1.disable = false;\n}\n\nfunction reward (S, A, R, _S) {\n    var mr = Math.max(...Q[_S]);\n    return Math.round(Q[S][A]*(1 - alpha) + alpha*(R + beta*mr));\n}\n\n// 繪圖\nforever(() =\u003e {\n    \n    btn1.opacity = btn1.disable ? 0.5 : 1;\n    btn2.opacity = btn2.disable ? 0.5 : 1;\n    btn3.opacity = btn3.disable ? 0.5 : 1;\n\n    for (var x = 0; x \u003c 6; x++) {\n        for (var y = 0; y \u003c 6; y++) {\n            pen.fillColor = 'black';\n\n            if (map[y][x] == 0) pen.fillColor = 'white';\n            if (map[y][x] == 1) pen.fillColor = 'black';\n            if (map[y][x] == 2) pen.fillColor = 'red';\n            pen.drawRect(110+x*w, 60+y*w, w-5, w-5);\n            \n            var s = Q[x+':'+y];\n            if (map[x][y] == 0) {\n                print(s[0], 110+x*w,    60+y*w+22, \"black\", 12);\n                print(s[1], 110+x*w+17, 60+y*w+45, \"black\", 12);\n                print(s[2], 110+x*w+30, 60+y*w+22, \"black\", 12);\n                print(s[3], 110+x*w+17, 60+y*w,    \"black\", 12);   \n            }\n        }\n    }\n    pen.fillColor = 'orange';\n    pen.drawRect(110+player.x*w, 60+player.y*w, w-5, w-5);\n    print(formula, 20, 20, 'black', 20);\n});","created_at":"2018-05-18T18:07:28.827+08:00","updated_at":"2019-10-19T21:55:10.288+08:00","name":"Q-learning","language":"javascript","screenshot":{"url":"/uploads/project/screenshot/28969/cd0f4788569754e6917dd57af8388304.jpg"},"parent_id":28963,"plugin":"","description":null,"note":null,"status":"public","like_student_ids":[],"is_featured":false,"views":503,"hashid":"kdms8jpd","is_content_changed":false,"review_status":"unsubmitted","submitted_at":null,"reviewed_at":null,"advise":null,"is_deleted":false}