Q-learning 迷宮 | JavaScript 程式專案

{"id":28963,"student_id":2591,"content":"let 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\nlet w = 60; // 繪圖的寬度\nlet player = {\n    x: 1, y: 1\n};\nlet sw = 0;\nlet Q = {};\nlet S = '1:1';\nlet A;\nlet _S;\n\nlet alpha = 0.7;\nlet beta = 0.8;\n\nlet i = 0;\nforever(function () {\n    // i++;\n    // if (i%2 == 0) update();\n});\n\nfunction update () {\n\n    _S = player.x + ':' + player.y\n\n    if (Q[S] === undefined) Q[S] = [0, 0, 0, 0];\n    if (Q[_S] === undefined) Q[_S] = [0, 0, 0, 0];\n    \n    let c = map[player.y][player.x];\n\n    if (c === 0) Q = reward(Q, S, A, -100, _S); // 白色\n    if (c == 1) Q = reward(Q, S, A, -1000, _S); // 黑洞\n    if (c == 2) Q = reward(Q, S, A, +3000, _S); // 寶藏\n\n    // 撞到黑洞或寶藏就重新開始\n    if (c == 1 || c == 2) {\n        player.x = 1;\n        player.y = 1;\n    } else {\n        S = _S;\n        A = Q[S].indexOf(Math.max(...Q[S]));\n        console.log(A+\":\"+player.x+\":\"+player.y);\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    }\n}\n\nfunction reward (Q, S, A, R, _S) {\n    let mr = Math.max(...Q[_S]);\n    Q[S][A] = Math.round(Q[S][A]*(1 - alpha) + alpha*(R + beta*mr));\n    return Q;\n}\n\n// 繪圖\nforever(() =\u003e {\n    for (let x = 0; x \u003c 7; x++) {\n        for (let y = 0; y \u003c 7; y++) {\n            pen.fillColor = 'black';\n            \n            if (x \u003c= 5 \u0026\u0026 y \u003c= 5) {\n                if (map[y][x] == 1) pen.fillColor = 'black';\n                else if (map[y][x] == 2) pen.fillColor = 'red';\n                else pen.fillColor = '#eee';\n                pen.drawRect(150+x*w, 60+y*w, w-5, w-5);\n                if (Q[x+':'+y]) {\n                    if (Q[x+':'+y][0] !== undefined) {\n                        if (Q[x+':'+y][0] != -Infinity) {\n                            print(Q[x+':'+y][0], 150+x*w, 60+y*w+22, \"black\", 12);\n                        }\n                    }\n                    if (Q[x+':'+y][1] !== undefined) {\n                        if (Q[x+':'+y][1] != -Infinity) {\n                            print(Q[x+':'+y][1], 150+x*w+17, 60+y*w+45, \"black\", 12);\n                        }\n                    }\n                    if (Q[x+':'+y][2] !== undefined) {\n                        if (Q[x+':'+y][2] != -Infinity) {\n                            print(Q[x+':'+y][2], 150+x*w+30, 60+y*w+22, \"black\", 12);\n                        }\n                    }\n                    if (Q[x+':'+y][3] !== undefined) {\n                        if (Q[x+':'+y][3] != -Infinity) {\n                            print(Q[x+':'+y][3], 150+x*w+17, 60+y*w, \"black\", 12);\n                        }\n                    }\n                }\n            }\n        }\n    }\n    pen.fillColor = 'orange';\n    pen.drawRect(150+player.x*w, 60+player.y*w, w-5, w-5);\n});\n\nsetInterval(function() {\n    if (sw)\n        update();\n}, 50);\n\nwhen('keydown', \"space\", function() {\n    sw = !sw\n});\nwhen(\"mousedown\", function() {\n    if (!sw) {\n        update();\n    }\n});\nfunction GetRound(num, len) {\n    return Math.round(num * Math.pow(10, len)) / Math.pow(10, len);\n}","created_at":"2018-05-18T17:48:07.916+08:00","updated_at":"2019-10-30T16:19:33.845+08:00","name":"Q-learning 迷宮","language":"javascript","screenshot":{"url":"https://cdn6.koding.school/uploads/project/screenshot/28963/23805f03ccff22654b03cb17c0dd5f4a.jpg"},"parent_id":28948,"plugin":"","description":null,"note":null,"status":"public","like_student_ids":[],"is_featured":false,"views":133,"hashid":"5j3sj3w8","is_content_changed":false,"review_status":"unsubmitted","submitted_at":null,"reviewed_at":null,"advise":null,"is_deleted":false}