| 158 | |
| 159 | == Dynamic Scripting == |
| 160 | |
| 161 | Dynamic scripting is a form of reinforcement learning used in adaptive game AI. |
| 162 | |
| 163 | [http://www.vectrlab.com/wp-content/uploads/DS_applied_to_FPS_Apr_6_19_09.pdf Dynamic Scripting FPS][[BR]] |
| 164 | [http://www.personeel.unimaas.nl/m-ponsen/pubs/iaai05ponsen.pdf Dynamic Scripting RTS][[BR]] |
| 165 | [http://www.google.com/url?sa=t&source=web&cd=1&ved=0CBkQFjAA&url=http%3A%2F%2Fciteseerx.ist.psu.edu%2Fviewdoc%2Fdownload%3Fdoi%3D10.1.1.137.591%26rep%3Drep1%26type%3Dpdf&rct=j&q=dynamic%20scripting%20computer%20game&ei=UgzpTa-gIpTUgQfN7KmmAQ&usg=AFQjCNGt98Mz3GLSzSHu1cJ3yrJMJLbkDg Dynamic Scripting RPG] |
| 166 | |
| 167 | There are four main components in the dynamic scripting algorithm: [[BR]] |
| 168 | 1. Set of rules - Rules that the algorithm can choose from. Each rule has a weight. |
| 169 | 2. Script selection - A subset of rules used in a learning episode. |
| 170 | 3. Rule policy - Determines how rules in a script are applied within an episode. |
| 171 | 3. Rule value updating - Reward function that provides feedback on the script. Success increases weights of rules, failure decreases weights of rules. |