A Day-to-Day Route Choice Model Based on Reinforcement Learning

<table>Flow evolution in the second test network with different <svg height="9.89089pt" id="M172" style="vertical-align:-0.2129898pt" version="1.1" viewbox="-0.0498162 -9.6779 3.75774 9.89089" width="3.75774pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.0135,0,0,-0.0135,0,0)"><path d="M238 681C243 705 239 712 230 712C217 712 156 682 75 674L70 648H105C148 648 153 641 144 598L39 110C18 11 35 -12 55 -12C90 -12 166 36 221 103L205 125C174 93 130 65 118 65C112 65 108 68 114 96L238 681Z" id="g113-109"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="269" vert-adv-y="269"></glyph.data></g></svg>-value when <svg height="12.2707pt" id="M173" style="vertical-align:-3.57194pt" version="1.1" viewbox="-0.0498162 -8.69876 31.0735 12.2707" width="31.0735pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.0135,0,0,-0.0135,0,0)"><path d="M642 419L635 448C586 435 552 411 532 392C518 379 509 351 496 304C484 260 462 196 445 150C424 93 388 40 314 30L413 508L406 510L344 491L257 36C205 46 175 84 175 169C175 195 180 241 185 277C189 304 190 331 190 358C190 413 175 448 141 448C111 448 69 429 23 373L30 347C51 365 68 375 81 375C93 375 108 368 108 327C108 307 104 268 101 239C98 211 95 180 95 155C95 33 159 -8 248 -14L213 -186C206 -220 221 -254 230 -261L261 -230L306 -11C339 -4 366 6 389 20C431 46 473 87 503 155C533 224 557 286 571 325C586 367 606 393 642 419Z" id="g113-245"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="654" vert-adv-y="654"></glyph.data></g><g transform="matrix(.0135,0,0,-0.0135,12.648,0)"><path d="M535 323V373H52V323H535ZM535 138V188H52V138H535Z" id="g117-34"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="587" vert-adv-y="587"></glyph.data></g><g transform="matrix(.0135,0,0,-0.0135,24.386,0)"><path d="M384 0V27C293 34 287 42 287 114V635C232 613 172 594 109 583V559L157 557C201 555 205 550 205 499V114C205 42 199 34 109 27V0H384Z" id="g113-50"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="480" vert-adv-y="480"></glyph.data></g></svg>.</table>

Mathematical Problems in Engineering

A Day-to-Day Route Choice Model Based on Reinforcement Learning

Figure 11