├── LICENSE ├── Project ├── Assets │ ├── Agent.cs │ ├── Agent.cs.meta │ ├── BanditEnvironment.cs │ ├── BanditEnvironment.cs.meta │ ├── Directional Light.controller │ ├── Directional Light.controller.meta │ ├── Gems.meta │ ├── Gems │ │ ├── Materials.meta │ │ ├── Materials │ │ │ ├── crystal_b.mat │ │ │ └── crystal_b.mat.meta │ │ ├── crystal_b2.png │ │ ├── crystal_b2.png.meta │ │ ├── large_diamond_blue.mtl │ │ ├── large_diamond_blue.mtl.meta │ │ ├── large_diamond_blue.obj │ │ └── large_diamond_blue.obj.meta │ ├── Level 1 Monster Pack.meta │ ├── Level 1 Monster Pack │ │ ├── Images.meta │ │ ├── Images │ │ │ ├── Slime.meta │ │ │ └── Slime │ │ │ │ ├── SlimeRed.jpg │ │ │ │ └── SlimeRed.jpg.meta │ │ ├── Materials.meta │ │ ├── Materials │ │ │ ├── Slime.meta │ │ │ └── Slime │ │ │ │ ├── SlimeMaterial.mat │ │ │ │ ├── SlimeMaterial.mat.meta │ │ │ │ ├── Slime_Red.mat │ │ │ │ └── Slime_Red.mat.meta │ │ ├── Models.meta │ │ ├── Models │ │ │ ├── Materials.meta │ │ │ ├── Materials │ │ │ │ ├── SlimeMaterial.mat │ │ │ │ └── SlimeMaterial.mat.meta │ │ │ ├── Slime_Level_1.fbx │ │ │ └── Slime_Level_1.fbx.meta │ │ ├── Prefabs.meta │ │ └── Prefabs │ │ │ ├── Slime.meta │ │ │ └── Slime │ │ │ ├── Slime_Red.prefab │ │ │ └── Slime_Red.prefab.meta │ ├── Materials.meta │ ├── Materials │ │ ├── Materials.meta │ │ ├── Materials │ │ │ ├── wall.mat │ │ │ └── wall.mat.meta │ │ ├── roof_texture.mat │ │ ├── roof_texture.mat.meta │ │ ├── value_est.mat │ │ ├── value_est.mat.meta │ │ ├── value_true.mat │ │ ├── value_true.mat.meta │ │ ├── wall.jpg │ │ ├── wall.jpg.meta │ │ ├── walls_3.mat │ │ └── walls_3.mat.meta │ ├── Resources.meta │ ├── Resources │ │ ├── bandit_chest.prefab │ │ ├── bandit_chest.prefab.meta │ │ ├── diamond.prefab │ │ ├── diamond.prefab.meta │ │ ├── slime.prefab │ │ ├── slime.prefab.meta │ │ ├── true_value.prefab │ │ ├── true_value.prefab.meta │ │ ├── value.prefab │ │ └── value.prefab.meta │ ├── SelectAction.cs │ ├── SelectAction.cs.meta │ ├── Treasure_Chest_Asset.meta │ ├── Treasure_Chest_Asset │ │ ├── Treasure_Chest.fbx │ │ ├── Treasure_Chest.fbx.meta │ │ ├── Treasure_Chest_Diffuse.tif │ │ ├── Treasure_Chest_Diffuse.tif.meta │ │ ├── Treasure_Chest_Material.mat │ │ ├── Treasure_Chest_Material.mat.meta │ │ ├── Treasure_Chest_Prefab.prefab │ │ └── Treasure_Chest_Prefab.prefab.meta │ ├── blue_light.anim │ ├── blue_light.anim.meta │ ├── scene.meta │ ├── scene.unity │ ├── scene.unity.meta │ └── scene │ │ ├── LightingData.asset │ │ ├── LightingData.asset.meta │ │ ├── ReflectionProbe-0.exr │ │ └── ReflectionProbe-0.exr.meta └── ProjectSettings │ ├── AudioManager.asset │ ├── ClusterInputManager.asset │ ├── DynamicsManager.asset │ ├── EditorBuildSettings.asset │ ├── EditorSettings.asset │ ├── GraphicsSettings.asset │ ├── InputManager.asset │ ├── NavMeshAreas.asset │ ├── NetworkManager.asset │ ├── Physics2DSettings.asset │ ├── ProjectSettings.asset │ ├── ProjectVersion.txt │ ├── QualitySettings.asset │ ├── TagManager.asset │ ├── TimeManager.asset │ └── UnityConnectSettings.asset ├── README.md └── photo.png /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /Project/Assets/Agent.cs: -------------------------------------------------------------------------------- 1 | using System.Collections; 2 | using System.Collections.Generic; 3 | using UnityEngine; 4 | using UnityEngine.UI; 5 | using System.Linq; 6 | 7 | public class Agent { 8 | public float[][] value_table; // The matrix containing the values estimates. 9 | float learning_rate = 0.005f; // The rate at which to update the value estimates given a reward. 10 | 11 | /// 12 | /// Initializes a new instance of the class. 13 | /// 14 | /// Number of possible states in the environment. 15 | /// Number of possible actions possible in the environment. 16 | /// If set to true, then initialize the value estimates as optimistically. 17 | public Agent(int stateSize, int actionSize, bool optimistic) { 18 | value_table = new float[stateSize][]; 19 | for (int i = 0; i < stateSize; i++) { 20 | value_table [i] = new float[actionSize]; 21 | for (int j = 0; j < actionSize; j++) { 22 | if (!optimistic) { 23 | value_table [i] [j] = 0.0f; 24 | } else { 25 | value_table [i] [j] = 1.0f; 26 | } 27 | } 28 | } 29 | } 30 | 31 | /// 32 | /// Picks an action to taken given a state. 33 | /// 34 | /// The action choosen by the agent's policy 35 | /// The current environment state 36 | public int PickAction(int state) { 37 | float confidence = 2.1f - GameObject.Find ("confidence_S").GetComponent ().value; 38 | float[] probs = softmax (value_table [state], confidence); 39 | float cumulative = 0.0f; 40 | int selectedElement = 0; 41 | float diceRoll = Random.Range (0f, 1f); 42 | for (int i = 0; i < probs.Length; i++) 43 | { 44 | cumulative += probs[i]; 45 | if (diceRoll < cumulative) 46 | { 47 | selectedElement = i; 48 | break; 49 | } 50 | } 51 | return selectedElement; 52 | } 53 | 54 | /// 55 | /// Updates the value estimate matrix given a new experience (state, action, reward). 56 | /// 57 | /// The environment state the experience happened in. 58 | /// The action choosen by the agent in the state. 59 | /// The reward recieved by the agent from the environment for it's action. 60 | public void UpdatePolicy(int state, int action, float reward) { 61 | value_table [state][action] += learning_rate * (reward - value_table[state] [action]); 62 | } 63 | 64 | /// 65 | /// Softmax the specified values with a given temperature. 66 | /// 67 | /// The values to be normalized using softmax. 68 | /// The desired temperature of the softmax distribution. 69 | /// A set of values with normalized probabilities which sum to 1. 70 | float[] softmax(float[] values, float temp) { 71 | float[] softmax_values = new float[values.Length]; 72 | float[] exp_values = new float[values.Length]; 73 | for (int i = 0; i < values.Length; i++) { 74 | exp_values [i] = Mathf.Exp (values [i] / temp); 75 | } 76 | 77 | for (int i = 0; i < values.Length; i++) { 78 | softmax_values[i] = exp_values[i] / exp_values.Sum(); 79 | } 80 | return softmax_values; 81 | } 82 | } 83 | -------------------------------------------------------------------------------- /Project/Assets/Agent.cs.meta: -------------------------------------------------------------------------------- 1 | fileFormatVersion: 2 2 | guid: a44a6e556fa2b49b9ae2246f0d25b21f 3 | timeCreated: 1496425007 4 | licenseType: Pro 5 | MonoImporter: 6 | serializedVersion: 2 7 | defaultReferences: [] 8 | executionOrder: 0 9 | icon: {instanceID: 0} 10 | userData: 11 | assetBundleName: 12 | assetBundleVariant: 13 | -------------------------------------------------------------------------------- /Project/Assets/BanditEnvironment.cs: -------------------------------------------------------------------------------- 1 | using System.Collections; 2 | using System.Collections.Generic; 3 | using UnityEngine; 4 | using UnityEngine.UI; 5 | using System.Linq; 6 | using UnityEngine.SceneManagement; 7 | 8 | public class BanditEnvironment : MonoBehaviour { 9 | 10 | public List chests; // List of chest objects. 11 | public List estimatedValues; // List of visualized value estimates (green orbs). 12 | public List trueValues; // List of visualized true values (clear orbs). 13 | public float totalRewards; // Total rewards obtained over the course of all trials. 14 | int trial; // Trial index. 15 | int num_arms; // Number of chests in a given trial. 16 | int totalStates; // Number of possible rooms with unique chest reward probabilties. 17 | int state; // Index of current room. 18 | public float actSpeed; // Speed at which actions are chosen. 19 | float[][] armProbs; // True probability values for each chest in each room. 20 | Agent agent; // The agent which learns to pick actions. 21 | 22 | // Use this for initialization 23 | void Start () { 24 | } 25 | 26 | /// 27 | /// Initialized the bandit game. Called when "Start Learning" button in clicked. 28 | /// 29 | public void BeginLearning() { 30 | trial = 0; 31 | totalRewards = 0; 32 | int stateMode = GameObject.Find ("state_D").GetComponent ().value; 33 | actSpeed = 0.5f - GameObject.Find ("speed_S").GetComponent ().value; 34 | if (stateMode == 0) { 35 | totalStates = 1; 36 | } else { 37 | totalStates = 3; 38 | } 39 | num_arms = GameObject.Find ("arms_D").GetComponent ().value + 2; 40 | bool optimistic = GameObject.Find ("optToggle").GetComponent ().isOn; 41 | 42 | agent = new Agent (totalStates, num_arms, optimistic); 43 | 44 | int diff = GameObject.Find ("diff_D").GetComponent ().value; 45 | float adjust = ((float)diff) * 0.1f; 46 | armProbs = new float[totalStates] []; 47 | for (int i = 0; i < totalStates; i++) { 48 | armProbs [i] = new float[num_arms]; 49 | int winner = Random.Range (0, num_arms); 50 | for (int j = 0; j < num_arms; j++) { 51 | if (j == winner) { 52 | armProbs [i] [j] = Random.Range (0.6f, 1.0f - adjust); 53 | } else { 54 | armProbs [i] [j] = Random.Range (0.0f + adjust, 0.4f); 55 | } 56 | } 57 | } 58 | 59 | GameObject[] startUI = (GameObject.FindGameObjectsWithTag ("loading")); 60 | foreach (GameObject obj in startUI) { 61 | Destroy (obj); 62 | } 63 | 64 | chests = new List (); 65 | estimatedValues = new List (); 66 | trueValues = new List (); 67 | 68 | GameObject.Find ("restartButton").GetComponent