From 58aa5df430d7072186948bbfd8e94873204b9fd4 Mon Sep 17 00:00:00 2001 From: Ugo Date: Thu, 12 Dec 2019 17:47:06 +0100 Subject: [PATCH] refactoring --- css/src/style.scss | 18 +- css/style.min.css | 2 +- index.html | 17 +- js/rl.js | 37 ++- js/view.js | 665 +++++++++++++++++++-------------------------- 5 files changed, 324 insertions(+), 415 deletions(-) diff --git a/css/src/style.scss b/css/src/style.scss index 60e6b1a..e9c900e 100644 --- a/css/src/style.scss +++ b/css/src/style.scss @@ -1,3 +1,4 @@ +// compileCompressed *{ margin: 0; padding: 0; @@ -22,12 +23,23 @@ nav{ left: 10px; } +button{ + margin: 0.3em; +} + .absolute{ position: absolute; top:0; left:0; } +.stage{ + display: flex; + justify-content: center; + align-items: center; + height: 100vh; +} + .plot{ position: absolute; top: 2vh; @@ -63,12 +75,12 @@ nav{ left: 50%; transform: translateX(-50%) translateY(-100%); z-index: 10; - width: 50%; - height: 40%; + max-width: 50%; background-color: #BBB; transition: all 1s; + &.active{ - top:50%; + top:20%; transform: translateX(-50%) translateY(-50%); } } diff --git a/css/style.min.css b/css/style.min.css index c44b7b9..95edaeb 100644 --- a/css/style.min.css +++ b/css/style.min.css @@ -1 +1 @@ -*{margin:0;padding:0}body{margin:0;padding:0;font-family:sans-serif}#container{height:100vh;position:relative}#canvas{height:100%}nav{position:absolute;top:10px;left:10px}.absolute{position:absolute;top:0;left:0}.plot{position:absolute;top:2vh;right:2vw;width:20vw;height:10vw}.sliders{position:absolute;top:20vh;left:2vw;width:20vw}#formula{position:absolute;top:71.5vh;width:90vw}.score{position:absolute;top:7vh;left:2vw;width:20vw}.lightbox{padding:2em;position:absolute;top:0;left:50%;transform:translateX(-50%) translateY(-100%);z-index:10;width:50%;height:40%;background-color:#BBB;transition:all 1s}.lightbox.active{top:50%;transform:translateX(-50%) translateY(-50%)} +*{margin:0;padding:0}body{margin:0;padding:0;font-family:sans-serif}#container{height:100vh;position:relative}#canvas{height:100%}nav{position:absolute;top:10px;left:10px}button{margin:0.3em}.absolute{position:absolute;top:0;left:0}.stage{display:flex;justify-content:center;align-items:center;height:100vh}.plot{position:absolute;top:2vh;right:2vw;width:20vw;height:10vw}.sliders{position:absolute;top:20vh;left:2vw;width:20vw}#formula{position:absolute;top:71.5vh;width:90vw}.score{position:absolute;top:7vh;left:2vw;width:20vw}.lightbox{padding:2em;position:absolute;top:0;left:50%;transform:translateX(-50%) translateY(-100%);z-index:10;max-width:50%;background-color:#BBB;transition:all 1s}.lightbox.active{top:20%;transform:translateX(-50%) translateY(-50%)} diff --git a/index.html b/index.html index c8ab5b1..8d52cca 100644 --- a/index.html +++ b/index.html @@ -3,7 +3,7 @@ - + @@ -23,14 +23,9 @@
- - - - + - - - + @@ -45,13 +40,11 @@
-

Current Score

+

Current Energy

{{machine.score}}

- + diff --git a/js/rl.js b/js/rl.js index ac93a6b..b3ed3ee 100644 --- a/js/rl.js +++ b/js/rl.js @@ -21,6 +21,10 @@ class RL_machine { this.epsilon = epsilon; this.q_table = this.actions_per_state.map((c) => c.reduce((o,n) => {o[n]=0; return o},{})); this.reset_machine(); + this.callback = null; + } + setCallback(cb){ + this.callback = cb; } reset_machine(){ for (var q in this.q_table){ @@ -34,12 +38,19 @@ class RL_machine { this.state = this.start_state; this.score = this.start_score; } - new_episode(){ + new_episode(reason = "failed"){ + const reset = () => { + this.episode++; + this.score_history.push(this.score); + this.state = this.start_state; + this.score = this.start_score; + } // add_new_episode_callback - this.episode++; - this.score_history.push(this.score); - this.state = this.start_state; - this.score = this.start_score; + if (!this.running && this.callback) { + this.callback(reason).then((p) => reset()); + } else { + reset(); + } } auto_step(){ if (Math.random() < this.epsilon){ @@ -55,23 +66,11 @@ class RL_machine { this.state = this.update_q_table(this.state, action); // add_new_step_callback if (this.end_states.indexOf(this.state) >= 0) { - var succ_event = new CustomEvent("episode",{ - detail: "success" - }); - if (!this.running) { - window.dispatchEvent(succ_event); - } - this.new_episode(); + this.new_episode("success"); return 2 } if (this.score <= this.end_score){ - var fail_event = new CustomEvent("episode",{ - detail: "failed" - }); - if (!this.running) { - window.dispatchEvent(fail_event); - } - this.new_episode(); + this.new_episode("failed"); return 2 } return 1 diff --git a/js/view.js b/js/view.js index 0b95a00..570602d 100644 --- a/js/view.js +++ b/js/view.js @@ -1,3 +1,21 @@ +// ---------------------------------------------------------------------------- +// ------------------------------- Utils -------------------------------------- +// ---------------------------------------------------------------------------- + +function defer() { + var res, rej; + + var promise = new Promise((resolve, reject) => { + res = resolve; + rej = reject; + }); + + promise.resolve = res; + promise.reject = rej; + + return promise; +} + // ---------------------------------------------------------------------------- // -------------------------------- Plot -------------------------------------- // ---------------------------------------------------------------------------- @@ -44,26 +62,7 @@ Vue.component('line-chart', { // --------------------------------- Map -------------------------------------- // ---------------------------------------------------------------------------- -function set_images($this){ - const robot_image = new window.Image(); - robot_image.src = "img/robot.png"; - // robot_image.src = "https://konvajs.org/assets/yoda.jpg"; - robot_image.onload = () => { - // set image only when it is loaded - $this.robot_image = robot_image; - }; - const energy_image = new window.Image(); - energy_image.src = "img/station.png"; - // energy_image.src = "https://konvajs.org/assets/yoda.jpg"; - energy_image.onload = () => { - // set image only when it is loaded - $this.energy_image = energy_image; - }; -} - -var palette = ['#d2000d', '#d30512', '#d40a17', '#d50f1c', '#d61420', '#d71a25', '#d71f2a', '#d8242f', '#d92934', '#da2e39', '#db333d', '#dc3842', '#dd3d47', '#de424c', '#df4751', '#e04d56', '#e0525a', '#e1575f', '#e25c64', '#e36169', '#e4666e', '#e56b73', '#e67077', '#e7757c', '#e87a81', '#e98086', '#e9858b', '#ea8a90', '#eb8f95', '#ec9499', '#ed999e', '#ee9ea3', '#efa3a8', '#f0a8ad', '#f1adb2', '#f2b3b6', '#f2b8bb', '#f3bdc0', '#f4c2c5', '#f5c7ca', '#f6cccf', '#f7d1d3', '#f8d6d8', '#f9dbdd', '#fae0e2', '#fbe6e7', '#fbebec', '#fcf0f0', '#fdf5f5', '#fefafa', '#ffffff', '#fafcfa', '#f5f9f5', '#f0f6f0', '#ebf3ec', '#e6f1e7', '#e1eee2', '#dcebdd', '#d7e8d8', '#d3e5d3', '#cee2cf', '#c9dfca', '#c4dcc5', '#bfd9c0', '#bad6bb', '#b5d4b6', '#b0d1b2', '#abcead', '#a6cba8', '#a1c8a3', '#9cc59e', '#97c299', '#92bf95', '#8dbc90', '#88b98b', '#84b786', '#7fb481', '#7ab17c', '#75ae77', '#70ab73', '#6ba86e', '#66a569', '#61a264', '#5c9f5f', '#579c5a', '#529a56', '#4d9751', '#48944c', '#439147', '#3e8e42', '#398b3d', '#348839', '#308534', '#2b822f', '#267f2a', '#217d25', '#1c7a20', '#17771c', '#127417', '#0d7112', '#086e0d'] - -Vue.component('rl-map', { +var MapBase = Vue.component('MapBase', { props: ['machine', 'maze', 'config'], data: function () { return { @@ -72,12 +71,21 @@ Vue.component('rl-map', { } }, created() { - set_images(this); + var $this = this; + const robot_image = new window.Image(); + robot_image.src = "img/robot.png"; + robot_image.onload = () => { + $this.robot_image = robot_image; + }; + const energy_image = new window.Image(); + energy_image.src = "img/station.png"; + energy_image.onload = () => { + $this.energy_image = energy_image; + }; }, computed: { main_config: function(){ return { - ...this.config, offset: { x: -(this.config.width-this.base_size*this.maze.width)/2, y: -(this.config.height-this.base_size*this.maze.height)/2, @@ -88,9 +96,13 @@ Vue.component('rl-map', { return { height: this.base_size, width: this.base_size, - x: this.base_size * this.machine.state.x, - y: this.base_size * this.machine.state.y, + x: this.center, + y: this.center, image: this.robot_image, + offset:{ + x: this.base_size/2, + y: this.base_size/2, + } } }, energy_config: function() { @@ -104,26 +116,12 @@ Vue.component('rl-map', { image: this.energy_image, } }, - base_size: function() { - return Math.min(this.config.height/this.maze.height, this.config.width/this.maze.width); - }, strokeW: function() { return this.base_size / 50; }, - extreme_q_values: function(){ - var max = -10*30; - var min = 10*30; - for (field in this.q_table) { - for (key in this.q_table[field]){ - if (this.q_table[field][key]max){ - max = this.q_table[field][key]; - } - } - } - return {min:min,max:max}; - } + base_size: function() { + return Math.min(this.config.height/this.maze.height, this.config.width/this.maze.width); + }, }, methods: { get_tile_type: function(state) { @@ -143,6 +141,86 @@ Vue.component('rl-map', { y: this.base_size * pos.y+this.base_size/2, } }, + get_tile_config: function(t_type) { + const layout = { + width: this.base_size, + height: this.base_size, + stroke: '#ddd', + strokeWidth: this.strokeW, + offset: { + x: this.base_size/2, + y: this.base_size/2, + } + }; + switch (t_type) { + case tile.regular: + return { + ...layout, + fill: '#fff', + opacity: 1, + } + case tile.end: + return { + ...layout, + fill: '#0eb500', + opacity: 1, + } + case tile.start: + return { + ...layout, + fill: '#ff0008', + opacity: 1, + } + case tile.dangerous: + return { + ...layout, + fill: '#FF7B17', + opacity: 1, + } + case tile.wall: + return { + ...layout, + fill: '#000000', + opacity: 1, + } + } + }, + }, +}) + +//----------------------------------------------------------------------------- + +var palette = ['#d2000d', '#d30512', '#d40a17', '#d50f1c', '#d61420', '#d71a25', '#d71f2a', '#d8242f', '#d92934', '#da2e39', '#db333d', '#dc3842', '#dd3d47', '#de424c', '#df4751', '#e04d56', '#e0525a', '#e1575f', '#e25c64', '#e36169', '#e4666e', '#e56b73', '#e67077', '#e7757c', '#e87a81', '#e98086', '#e9858b', '#ea8a90', '#eb8f95', '#ec9499', '#ed999e', '#ee9ea3', '#efa3a8', '#f0a8ad', '#f1adb2', '#f2b3b6', '#f2b8bb', '#f3bdc0', '#f4c2c5', '#f5c7ca', '#f6cccf', '#f7d1d3', '#f8d6d8', '#f9dbdd', '#fae0e2', '#fbe6e7', '#fbebec', '#fcf0f0', '#fdf5f5', '#fefafa', '#ffffff', '#fafcfa', '#f5f9f5', '#f0f6f0', '#ebf3ec', '#e6f1e7', '#e1eee2', '#dcebdd', '#d7e8d8', '#d3e5d3', '#cee2cf', '#c9dfca', '#c4dcc5', '#bfd9c0', '#bad6bb', '#b5d4b6', '#b0d1b2', '#abcead', '#a6cba8', '#a1c8a3', '#9cc59e', '#97c299', '#92bf95', '#8dbc90', '#88b98b', '#84b786', '#7fb481', '#7ab17c', '#75ae77', '#70ab73', '#6ba86e', '#66a569', '#61a264', '#5c9f5f', '#579c5a', '#529a56', '#4d9751', '#48944c', '#439147', '#3e8e42', '#398b3d', '#348839', '#308534', '#2b822f', '#267f2a', '#217d25', '#1c7a20', '#17771c', '#127417', '#0d7112', '#086e0d'] + + +Vue.component('rl-map', { + extends: MapBase, + computed: { + robot_config: function() { + return { + height: this.base_size, + width: this.base_size, + x: this.base_size * this.machine.state.x, + y: this.base_size * this.machine.state.y, + image: this.robot_image, + } + }, + extreme_q_values: function(){ + var max = -10*30; + var min = 10*30; + for (field in this.q_table) { + for (key in this.q_table[field]){ + if (this.q_table[field][key]max){ + max = this.q_table[field][key]; + } + } + } + return {min: min, max: max}; + } + }, + methods: { get_q_text_config: function (val, i) { var off, key; switch (i) { @@ -209,7 +287,7 @@ Vue.component('rl-map', { break; } var $this = this; - var norma_value = value>0?(value+1000)/(2000):(value+30)/60; + var norma_value = value>0 ? (value+1000)/(2000) : (value+30)/60; return { sceneFunc: function(context, shape) { context.beginPath(); @@ -225,10 +303,6 @@ Vue.component('rl-map', { context.lineTo($this.base_size/2-stumpf, -width/2); context.lineTo($this.base_size/2-stumpf-arrow_l, -width/2); context.lineTo($this.base_size/2-stumpf-arrow_l, width/2); - // context.moveTo(0, 0); - // context.lineTo($this.base_size / 2, $this.base_size / 2); - // context.lineTo($this.base_size / 2, -$this.base_size / 2); - // context.lineTo(0, 0); context.closePath(); // (!) Konva specific method, it is very important context.fillStrokeShape(shape); @@ -239,90 +313,23 @@ Vue.component('rl-map', { rotation: rot, } }, - get_tile_config: function(i, t_type, local = false) { - // var pos = this.s2p(i); - var over = {}; - - // not in plus - if (local) { - if (!this.in_plus(this.machine.s2p(i), { - x: Math.round(this.machine.state.x), - y: Math.round(this.machine.state.y) - })) { - over = { - opacity: 0, - fill: "#eee" - }; - } else if (i != this.p2s(Math.round(this.machine.state.x), Math.round(this.machine.state.y))) { - over = { - opacity: 1, - fill: "#eee" - }; - } - } - const layout = { - width: this.base_size, - height: this.base_size, - stroke: '#ddd', - strokeWidth: this.strokeW, - offset: { - x: this.base_size/2, - y: this.base_size/2, - } - }; - switch (t_type) { - case tile.regular: - return { - ...layout, - fill: '#fff', - opacity: 1, - ...over, - } - case tile.end: - return { - ...layout, - fill: '#0eb500', - opacity: 1, - ...over, - } - case tile.start: - return { - ...layout, - fill: '#ff0008', - opacity: 1, - ...over, - } - case tile.dangerous: - return { - ...layout, - fill: '#FF7B17', - opacity: 1, - ...over, - } - case tile.wall: - return { - ...layout, - fill: '#000000', - opacity: 1, - ...over, - } - } - }, }, template: - ` - - - - + ` + + + + + + + + + + + - - - - - - - ` + + ` }) // ---------------------------------------------------------------------------- @@ -330,27 +337,17 @@ Vue.component('rl-map', { // ---------------------------------------------------------------------------- Vue.component('rl-local', { - props: ['machine', 'maze', 'config'], - data: function () { - return { - robot_image: null, - energy_image: null, - } - }, - created() { - set_images(this); - }, + extends: MapBase, computed: { main_config: function(){ return { - ...this.config, offset: { x: -(this.config.width-this.base_size*3)/2, y: -(this.config.height-this.base_size*3)/2, } } }, - map_config: function() { + local_config: function() { return { x: -(this.machine.state.x)*this.base_size, y: -(this.machine.state.y)*this.base_size, @@ -360,181 +357,160 @@ Vue.component('rl-local', { } } }, - robot_config: function() { - return { - height: this.base_size, - width: this.base_size, - x: this.center, - y: this.center, - image: this.robot_image, - offset:{ - x: this.base_size/2, - y: this.base_size/2, - } - } - }, - energy_config: function() { - return { - height: this.base_size, - width: this.base_size, - offset: { - x: this.base_size/2, - y: this.base_size/2 - }, - image: this.energy_image, - } - }, base_size: function() { return Math.min(this.config.height/3, this.config.width/3); }, center: function() { return 3*this.base_size / 2; }, - strokeW: function() { - return this.base_size / 50; + local_area: function() { + const x = Math.round(this.machine.state.x); + const y = Math.round(this.machine.state.y); + let arr = [[x,y-1],[x+1,y],[x,y+1],[x-1,y],[x,y]]; + return arr.filter((p) => p[0] < this.maze.width && p[1] < this.maze.height && + p[0] >= 0 && p[1] >= 0) + .map((p) => [this.maze.map[p[1]][p[0]], p[1]*this.maze.width+p[0]]); }, }, methods: { - get_tile_type: function(state) { - var pos = this.machine.s2p(state); - if (pos.y > maze.height) { - return null; - } else if (pos.x > maze.width) { - return null; - } else { - return maze.map[pos.y][pos.x]; - } + end: function(pos){ + return this.maze.get_states(tile.end).indexOf(pos) >= 0; }, - in_plus: function(pos1, pos2) { - if (Math.abs(pos1.x - pos2.x) + Math.abs(pos1.y - pos2.y) < 2) { - return true; + id_to_dir: function(id){ + switch (id) { + case 0: + return dir.UP; + case 1: + return dir.RIGHT; + case 2: + return dir.DOWN; + case 3: + return dir.LEFT; + default: + return undefined; } - return false; }, - get_field_config: function(state) { - var pos = this.machine.s2p(state); - return { - x: this.base_size * pos.x+this.base_size/2, - y: this.base_size * pos.y+this.base_size/2, - } + handleMouseEnter(e) { + const stage = e.target.getStage(); + stage.container().style.cursor = "pointer"; + }, + handleMouseLeave(e) { + const stage = e.target.getStage(); + stage.container().style.cursor = "default"; }, - get_tile_config: function(i, t_type, local = true) { + get_local_tile_config: function(i, t_type) { // var pos = this.s2p(i); + // in plus var over = {}; - // not in plus - if (local) { - if (!this.in_plus(this.machine.s2p(i), { - x: Math.round(this.machine.state.x), - y: Math.round(this.machine.state.y) - })) { - over = { - opacity: 0, - fill: "#eee" - }; - } else if (i != this.machine.p2s(Math.round(this.machine.state.x), Math.round(this.machine.state.y))) { - over = { - opacity: 1, - fill: "#eee" - }; + if (i != this.machine.p2s(Math.round(this.machine.state.x), Math.round(this.machine.state.y)) && + t_type != tile.wall) { + over = { + width: this.base_size, + height: this.base_size, + stroke: '#ddd', + strokeWidth: this.strokeW, + offset: { + x: this.base_size/2, + y: this.base_size/2, + }, + opacity: 1, + fill: "#eee", } } - const layout = { - width: this.base_size, - height: this.base_size, - stroke: '#ddd', - strokeWidth: this.strokeW, - offset: { - x: this.base_size/2, - y: this.base_size/2, - } - }; - switch (t_type) { - case tile.regular: - return { - ...layout, - fill: '#fff', - opacity: 1, - ...over, - } - case tile.end: - return { - ...layout, - fill: '#0eb500', - opacity: 1, - ...over, - } - case tile.start: - return { - ...layout, - fill: '#ff0008', - opacity: 1, - ...over, - } - case tile.dangerous: - return { - ...layout, - fill: '#FF7B17', - opacity: 1, - ...over, - } - case tile.wall: - return { - ...layout, - opacity: 1, - ...over, - fill: '#000000', - } - } + return over; }, }, template: - ` - - - - + ` + + + + + + + - - - ` + + + ` }) +Vue.component('navi-gation', { + props: ["options"], + template: ` + ` +}); + // ---------------------------------------------------------------------------- // ------------------------------ lightbox ------------------------------------ // ---------------------------------------------------------------------------- -Vue.component('light-box', { - props: ['content', 'options', 'active'], - // data: function () { - // return { - // active: false, - // } - // }, - // methods: { - // close: function() { - // this.active = false; - // }, - // open: function() { - // this.active = true; - // }, - // }, +var light_box = { + data: { + content: "", + options: [], + active: false, + }, + methods:{ + close: function(){ + this.active = false; + }, + popup: function(content, options){ + this.content = content; + var answer = defer(); + var $this = this; + this.options = options.reduce((old, opt) => { + old[opt] = function(){ + $this.active = false; + answer.resolve(opt); + } + return old + }, {}); + this.active = true; + return answer; + } + }, template: `
{{ content }}
- +
` -}) +} + +const PopupLibrary = { + install(Vue, options = {}) { + const root = new Vue(light_box) + + // Mount root Vue instance on new div element added to body + root.$mount(document.body.appendChild(document.createElement('div'))) + + Vue.prototype.$lightbox = root; + } +} + +window.Vue.use(PopupLibrary) // ---------------------------------------------------------------------------- // -------------------------------- Main -------------------------------------- // ---------------------------------------------------------------------------- - -function make_machine_reactive(th, machine){ +function makeMachineReactive(th, machine){ var $this = th; + $this.machine.s2p = function(state) { + return { + x: (state % $this.maze.width), + y: Math.floor(state / $this.maze.width), + } + }; + $this.machine.p2s = function(x, y) { + return x + y * $this.maze.width; + }; + // Score wrapper var s = machine.score; $this.machine.score = s; @@ -565,7 +541,7 @@ function make_machine_reactive(th, machine){ // State wrapper var s = machine.state; - $this.machine.state = $this.s2p(s); + $this.machine.state = $this.machine.s2p(s); Object.defineProperty(machine, 'state', { get: function() { return this._state @@ -577,21 +553,7 @@ function make_machine_reactive(th, machine){ }); machine.state = s; - $this.machine.s2p = $this.s2p; - $this.machine.p2s = $this.p2s; - - window.addEventListener("episode", (ev) => { - if (ev.detail == "failed"){ - $this.lightText = "Out of battery. The robot will be resetted."; - } else if (ev.detail == "success"){ - $this.lightText = "You reached the goal. The robot will be resetted."; - } - $this.lightOptions = { - "ok": () => {$this.lightpopup = false;}, - } - $this.lightpopup = true; - }) - + $this.machine.object.setCallback($this.onNewEpisode); } app = new Vue({ @@ -600,7 +562,7 @@ app = new Vue({ VueSlider: window['vue-slider-component'], }, data: { - state: 0, + state: null, maze: maze, machine: { object: machine, @@ -620,21 +582,15 @@ app = new Vue({ }, width: 0, height: 0, - state: null, components: [], - lightText: "", - lightOptions: "", - lightpopup: false, navigation: {}, - onEnterState: function(){}, - onLeaveState: function(){}, }, created() { // Resize handler window.addEventListener('resize', this.handleResize) this.handleResize(); - make_machine_reactive(this, machine); + makeMachineReactive(this, machine); this.state = "init"; }, destroyed() { @@ -643,14 +599,8 @@ app = new Vue({ computed: { stage_config: function() { return { - width: this.width, - height: this.height, - } - }, - map_config: function() { - return { - x: this.width*0.25, - y: this.height*0.1, + x: 0, + y: 0, width: this.width*0.5, height: this.height*0.8, } @@ -707,23 +657,16 @@ app = new Vue({ }, }, methods: { - s2p: function(state) { - return { - x: (state % this.maze.width), - y: Math.floor(state / this.maze.width), - } - }, - p2s: function(x, y) { - return x + y * this.maze.width; - }, + onEnterState: function(){}, + onLeaveState: function(){}, handleState: function(s) { if (!this.machine.object.running) { this.machine.state_tween.to(this.machine.state, 0.2, { - x: this.s2p(s).x, - y: this.s2p(s).y + x: this.machine.s2p(s).x, + y: this.machine.s2p(s).y }); } else { - this.machine.state = this.s2p(s); + this.machine.state = this.machine.s2p(s); } }, handleResize: function() { @@ -735,23 +678,29 @@ app = new Vue({ }, changeState: function(state){ this.components = []; - this.lightText = ""; - this.lightOptions = ""; - this.lightpopup = false; this.navigation = {}; this.onEnterState = function(){}; this.onLeaveState = function(){}; this.state = state; + }, + onNewEpisode: function(result){ + var text; + if (result == "failed"){ + text = "Out of battery. The robot will be resetted."; + } else if (result == "success"){ + text = "You reached the goal. The robot will be resetted."; + } + return this.$lightbox.popup(text, ["ok"]); } }, watch: { 'machine.learning_rate': function(new_val) { machine.lr = new_val; - render_latex(); + renderLatex(); }, 'machine.discount_factor': function(new_val) { machine.df = new_val; - render_latex(); + renderLatex(); }, 'machine.epsilon': function(new_val) { machine.epsilon = new_val; @@ -764,11 +713,11 @@ app = new Vue({ } }) -function render_latex() { +function renderLatex() { // (1-lr) * Q[state, action] + lr * (reward + gamma * np.max(Q[new_state, :]) katex.render(`Q(s,a)\\leftarrow${(1-machine.lr).toFixed(2)}Q(s,a)+${machine.lr.toFixed(2)}(reward + ${machine.df.toFixed(2)}\\max_{a'}(Q(s_{new}, a'))`, document.getElementById('formula'),{displayMode: true,}); } -render_latex(); +renderLatex(); @@ -778,34 +727,23 @@ render_latex(); var StateMgr = { init: { - lightText: `Reinforcement learning (RL) is an area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. (wikipedia) - This exhibit explains how a robot can learn to navigate through a maze in order to reach its destination, before running out of power. At first the robot knows nothing, and learns from each new action (movement) and state (location reached). Slowly it starts to develop an understanding of the maze that will allow it to reach the charging station before it runs out of power. Eventually, it should learn to avoid any detour and reach the charging station in the optimal number of steps.`, - lightOptions: { - "next": () => app.changeState("local"), - }, onEnterState: function () { - this.lightpopup = true; + var lightText = `Reinforcement learning (RL) is an area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. (wikipedia) + This exhibit explains how a robot can learn to navigate through a maze in order to reach its destination, before running out of power. At first the robot knows nothing, and learns from each new action (movement) and state (location reached). Slowly it starts to develop an understanding of the maze that will allow it to reach the charging station before it runs out of power. Eventually, it should learn to avoid any detour and reach the charging station in the optimal number of steps.` + this.$lightbox.popup(lightText, ["next"]).then((r) => this.changeState("local")); }, - onLeaveState: function () { - this.lightpopup = false; - } }, local: { components: ["local", "navi", "score"], navigation: { "reset robot": () => machine.reset_machine(), - "continue": () => app.changeState("global"), - }, - lightText: "But there is a problem! The robot cannot see the whole maze, it only knows where it is and in which direction it can move. Can you reach the charging station in those conditions? Use the arrows to move", - lightOptions: { - "next": () => {app.lightpopup = false;}, + "continue": null, }, onEnterState: function () { - this.lightpopup = true; + this.navigation.continue = () => this.changeState("global"); + var lightText = "But there is a problem! The robot cannot see the whole maze, it only knows where it is and in which direction it can move. Can you reach the charging station in those conditions? Use the arrows to move"; + this.$lightbox.popup(lightText, ["next"]); }, - onLeaveState: function () { - this.lightpopup = false; - } }, global: { components: ["global", "sliders", "plot", "navi", "score"], @@ -816,44 +754,11 @@ var StateMgr = { "greedy step!": () => machine.greedy_step(), "reset machine": () => machine.reset_machine(), }, - lightText: `As a human, you keep track of where you are and how you got there without thinking, which helps you think about what actions you should take next to reach your destination. And you can also just look around! How can then the robot 'think' of the maze, to know which action is the best at every moment? And how can it learn that? It must somehow keep track of where it is, and remember how good or bad was each action at each place in the maze, try new things, and update it's "mental image" of what was a good decision and what not. - - Reinforcement Learning uses the concept of a "Q-function", which keeps track of how "good" it expects it to be to take a specific action 'a' from a specific location 's'. This is written as Q(s, a). It also uses a "policy", which determines the best action to take in a given state, and is written as π(s). The robot must learn those functions while it navigates the maze. With each step, the functions are modified by a little bit, until eventually they give it the best strategy to solve the maze.`, - lightOptions: { - "continue": () => {app.lightpopup = false;}, - }, onEnterState: function () { - this.lightpopup = true; + var lightText = `As a human, you keep track of where you are and how you got there without thinking, which helps you think about what actions you should take next to reach your destination. And you can also just look around! How can then the robot 'think' of the maze, to know which action is the best at every moment? And how can it learn that? It must somehow keep track of where it is, and remember how good or bad was each action at each place in the maze, try new things, and update it's "mental image" of what was a good decision and what not. + + Reinforcement Learning uses the concept of a "Q-function", which keeps track of how "good" it expects it to be to take a specific action 'a' from a specific location 's'. This is written as Q(s, a). It also uses a "policy", which determines the best action to take in a given state, and is written as π(s). The robot must learn those functions while it navigates the maze. With each step, the functions are modified by a little bit, until eventually they give it the best strategy to solve the maze.`; + this.$lightbox.popup(lightText, ["continue"]); }, } }; - - -// ---------------------------------------------------------------------------- -// ------------------------------- Dummy -------------------------------------- -// ---------------------------------------------------------------------------- - -// Vue.component('dummy', { -// props: ['config'], -// data: function () { -// return { -// robot_image: null, -// } -// }, -// created() { -// -// }, -// mounted() { -// -// }, -// computed: { -// fun: function() { -// return -// }, -// }, -// methods: { -// fun: function(arg) { -// }, -// }, -// template: `` -// })