報酬駆動型システムの変更点

追加された行はこの色です。
削除された行はこの色です。
報酬駆動型システムへ行く。
報酬駆動型システムの差分を削除
#author("2024-02-02T02:53:56+00:00","","")
#author("2024-06-18T01:55:15+02:00","","")
[[由利恵]]




#ref(報酬駆動型システム.pdf)

*はじめに [#rb70a516]

[[自律分散的:https://wa3.i-3-i.info/word12359.html]]~

[[ペイオフ:https://xtech.nikkei.com/it/article/Keyword/20070207/261100/]]~

[[神経回路:https://kotobank.jp/word/%E7%A5%9E%E7%B5%8C%E5%9B%9E%E8%B7%AF-298112]]~

[[ナッシュ均衡:http://nabenavi.net/nash-equilibrium/]]

[[ナッシュ均衡python:https://note.com/sk_game_theory/n/n0f359e977d28]]

[[有限標準形ゲーム:https://www.jstage.jst.go.jp/article/jssst/29/2/29_2_69/_pdf]]

[[効用関数:https://kitaguni-economics.com/utility-function/]]

[[漸近安定:https://selife5.com/zenkinantei-antei-differ/]]


**1. 非協力ゲーム [#eca13243]

[[①:http://nabenavi.net/noncooperative_vs_cooperative/]]

[[②:http://nabenavi.net/tag/%E9%9D%9E%E5%8D%94%E5%8A%9B%E3%82%B2%E3%83%BC%E3%83%A0/]]

[[戦略空間:https://www.weblio.jp/wkpja/content/%E6%88%A6%E7%95%A5_%E3%82%B2%E3%83%BC%E3%83%A0%E7%90%86%E8%AB%96%E3%81%AB%E3%81%8A%E3%81%91%E3%82%8B%E6%88%A6%E7%95%A5]]

**2. ペイオフ双行列 [#p5acf4c3]

#ref(argmax.py)

**3. 混合戦略 [#o0099a27]

[[①:http://nabenavi.net/mixed-strategy/]]

[[②python:https://qiita.com/SaitoTsutomu/items/eeb19fc086640562513e]]

[[③:https://keiei-manabu.com/game-theory/mix.html]]

[[効用関数:https://kitaguni-economics.com/utility-function/]]


**4. 複製方程式（Replicator Dynamics） [#gdad0a64]

[[①:https://academic-accelerator.com/encyclopedia/jp/replicator-equation]]

[[②:http://evogame.in.coocan.jp/lectures/evogame-intro/no1.htm]]

**5. 遺伝子モデル [#x26a5592]

[[②:https://www.cis.twcu.ac.jp/~asakawa/study/Moribook2000-web.pdf]]

**6. 結合振動子 [#m29e91ea]

**7. 神経回路モデル [#ee555260]

**8. 勾配系，ポテンシャル [#jd692014]

**9. N人進化ゲーム [#m5759290]

**10. 適者生存 [#e4673279]

[1][[The theory of evolution and dynamical systems:https://cir.nii.ac.jp/crid/1130282271702081536]]
&br;
[2][[Stability theory of synchronized motion in coupled-oscillator systems.Ⅱ:https://academic.oup.com/ptp/article-abstract/70/5/1240/1940568?login=true]]
#ref(参考文献2.pdf)
[3][[複雑系のカオス的シナリオ:https://cir.nii.ac.jp/crid/1572543024944695424]]
&br;
[4][[ゲーム理論的均衡解探索のための疑似勾配系モデルのニューラルネットワーク実現とその挙動:https://www.jstage.jst.go.jp/article/iscie1988/12/11/12_11_680/_article/-char/ja/]]
#ref(参考文献4.pdf)
[5][[適者生存型学習則を適用した競合動径基底関数ネットワーク:https://www.jstage.jst.go.jp/article/iscie1988/12/11/12_11_680/_article/-char/ja/]]
COLOR(red):[5][[適者生存型学習則を適用した競合動径基底関数ネットワーク:https://www.jstage.jst.go.jp/article/iscie1988/12/11/12_11_680/_article/-char/ja/]]
#ref(参考文献5.pdf)

[6][[Reproductive and competitive radial basis function networks adaptable to dynamical environments:https://onlinelibrary.wiley.com/doi/abs/10.1002/1520-684X(20001130)31:13%3C65::AID-SCJ7%3E3.0.CO;2-K]]
&br;
[6'][[環境の変化に適応できる複製・競合動径基底関数ネットワーク:https://search.ieice.org/bin/pdf_link.php?category=D2&lang=J&year=1999&fname=j82-d2_5_941&abst=]]
#ref(参考文献6'.pdf)
[7][[On the V-stability of complex dynamical networks:https://www.sciencedirect.com/science/article/abs/pii/S0005109807000246]]
#ref(参考文献7.pdf)
[8][[Pinning a complex dynamical network to its equilibrium:https://ieeexplore.ieee.org/abstract/document/1344229]]
&br;
[8'][[Pinning complex networks by a single controller:https://arxiv.org/pdf/0707.2411.pdf]]
&br;
[8''][[Synchronization via pinning control on general complex networks:https://epubs.siam.org/doi/abs/10.1137/100781699]]
#ref(参考文献8''.pdf)
&br;
[8'''][[Adaptive outer synchronization between two complex delayed dynamical networks via aperiodically intermittent pinning control:https://www.sciencedirect.com/science/article/abs/pii/S0925231216311444]]
&br;
#ref(参考文献8'''.pdf)
&br;
[9][[The Simple Genetic Algorithm:https://books.google.co.jp/books?hl=ja&lr=lang_ja%7Clang_en&id=yAg-mAkx0yAC&oi=fnd&pg=PP17&dq=The+Simple+Genetic+Algorithm&ots=JWovMS5uPJ&sig=Bk6whSKx_P4dnoM4zLJQcjbRet4&redir_esc=y#v=onepage&q=The%20Simple%20Genetic%20Algorithm&f=false]]
&br;
[10][[Efficient computation of optimal actions:https://www.pnas.org/doi/abs/10.1073/pnas.0710743106]]
#ref(参考文献10.pdf)
&br;
[11][[Learning to Design Synergetic Computers with an Extended Symmetric Diffusion Network:https://direct.mit.edu/neco/article/11/6/1475/6290/Learning-to-Design-Synergetic-Computers-with-an]]
#ref(参考文献11.pdf)

[12][[Dale則を考慮したシナプス可逆性方程式の解析:https://www.jstage.jst.go.jp/article/iscie1988/8/12/8_12_718/_article/-char/ja/]]
COLOR(red):[12][[Dale則を考慮したシナプス可逆性方程式の解析:https://www.jstage.jst.go.jp/article/iscie1988/8/12/8_12_718/_article/-char/ja/]]

#ref(参考文献12.pdf)

[13]一般Lotka-Volterra競争系

[14]非線形力学の応用

[15]複合系のカオス

[16]Dynamical Behavior of a Chaos Nenural Network of an Associative schema Model

[17]カオス要素の

[18]淘汰・突然変異
報酬駆動型システム の変更点
