%function?[]?=?binary_bandit_exps（nBnPp_win）
%?
%?Duplicates?the?binary?bandit?experiments.
%?
%?Inputs:?
%???nB:?the?number?of?bandits
%???nP:?the?number?of?plays?（times?we?will?pull?a?arm）
%???p_win:?p_win（i）?is?the?probability?we?win?when?we?pull?arm?i.
%?
%?Written?by:
%?--?
%?John?L.?Weatherwax????????????????2007-11-13
%?
%?email:?wax@alum.mit.edu
%?
%?Please?send?comments?and?especially?bug?reports?to?the
%?above?email?address.
%?
%-----

%close?all;?
%clc;?
%clear;?

%?if（?nargin<1?）?%?the?number?of?bandits:?
%???nB?=?2000;??
%?end
%?if（?nargin<2?）?%?the?number?of?plays?（times?we?will?pull?a?arm）:
%???nP?=?2000;?
%?end
%?if（?nargin<3?）
%???p_win?=?[?0.1?0.2?];?
%???p_win?=?[?0.8?0.9?];?
%?end

%?the?number?of?arms:?
nA?=?2;?
????????
[dumbestArm]?=?max（?p_win?）;?

%randn（‘seed‘0）;?

if（?1?）?
??%?run?the?SUPERVISED?experiment?for?two?epsilon:
??%?0???=>?fully?greedy
??%?0.1?=>?inbetween?
??%?1.0?=>?explore?on?each?trial
??epsArray?=?[?0?0.1?];
??
??perOptAction?=?zeros（length（epsArray）nP）;?
??for?ei=1:length（epsArray）?
????tEps?=?epsArray（ei）;?
????
????pickedMaxAction?=?zeros（nBnP）;?
????for?bi=1:nB?%?pick?a?bandit
??????%?pick?an?arm?to?play?initially?...?
??????%arm?=?1;?
??????[dumarm]?=?histc（rand（1）linspace（01+epsnA+1））;?clear?dum;?
??????for?pi=1:nP?%?make?a?play
????????%?determine?if?this?move?is?exploritory?or?greedy:?
????????if（?rand（1）?<=?tEps?）?%?pick?a?RANDOM?arm:?
??????????[dumarm]?=?histc（rand（1）linspace（01+epsnA+1））;?clear?dum;?
????????end
????????if（?arm==1?）?otherArm=2;?else?otherArm=1;?end
????????%?determine?if?the?arm?selected?is?the?best?possible:?
????????if（?arm==bestArm?）?pickedMaxAction（bipi）=1;?end
????????%?get?the?reward?from?drawing?on?that?arm:?
????????prob?=?p_win（arm）;
????????if（?rand（1）?<=?prob?）????????????????%?this?arm?gave?SUCCESS?keep?playing?it?...
??????????%?do?nothing?...?
????????else?????????????????????????????????%?this?arm?gave?FAILURE?switch?to?the?other?...
??????????arm?=?otherArm;?
????????end
??????end
????end
????
????percentOptAction???=?mean（pickedMaxAction1）;
????perOptAction（ei:）?=?percentOptAction（:）.‘;????
??end
end


%------------------------------------------------------------------------
%?Learning?with?the?L_{R-P}?（linear?reward?penalty）?algorithm:?
%------------------------------------------------------------------------
alpha?=?0.1;?
if（?1?）?
??perOptActionRP?=?zeros（1nP）;?
????
??%qT?=?zeros（?nB?nA?）;??%?initialize?to?zero?the?probability?this?arm?gives?a?success?（no?knowledge）
??qT?=?0.5*ones（?nB?nA?）;??%?initialize?to?uniform?the?probability?this?arm?gives?a?success?（no?knowledge）
????
??pickedMaxAction?=?zeros（nBnP）;?
??for?bi=1:nB?%?pick?a?bandit
????for?pi=1:nP?%?make?a?play
??????%?pick?an?arm?based?on?the?distribution?in?qT:?
??????if（?rand（1）?????????arm?=?1;?
??????else
????????arm?=?2;?
??????end
??????if（?arm==1?）?otherArm=2;?else?otherArm=1;?end
??????%?determine?if?the?arm?selected?is?the?best?possible:?
??????if（

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件???????5861??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\binary_bandit_exps.m

?????文件????????791??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\binary_bandit_exps_script.m

?????文件???????5069??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\exercise_2_11.m

?????文件????????590??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\exercise_2_11_script.m

?????文件???????4401??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\exercise_2_5.m

?????文件???????4056??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\exercise_2_7.m

?????文件???????1159??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\exercise_2_7_script.m

?????文件???????4603??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\n_armed_testbed.m

?????文件???????5122??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\n_armed_testbed_softmax.m

?????文件???????3739??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\opt_initial_values.m

?????文件????????777??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\opt_initial_values_script.m

?????文件???????5405??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\persuit_method.m

?????文件????????592??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\persuit_method_script.m

?????文件???????4663??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\reinforcement_comparison_methods.m

?????文件????????887??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\reinforcement_comparison_methods_script.m

?????文件????????962??2010-09-28?17:14??suntton強化學習書籍代碼\Chapter?2?（Evaluative?Feedback）\sample_discrete.m

?????文件???????2712??2010-09-28?17:15??suntton強化學習書籍代碼\Chapter?3?（The?Reinforcement?Learning?Problem）\rr_action_bellman.m

?????文件???????2083??2010-09-28?17:15??suntton強化學習書籍代碼\Chapter?3?（The?Reinforcement?Learning?Problem）\rr_state_bellman.m

?????文件???????1732??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\cmpt_P_and_R.m

?????文件????????301??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\ex_4_2_sys_solv.m

?????文件???????2771??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\ex_4_5_policy_evaluation.m

?????文件???????3893??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\ex_4_5_policy_improvement.m

?????文件???????1422??2010-09-28?17:17??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\ex_4_5_rhs_state_value_bellman.m

?????文件???????3162??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\ex_4_5_script.m

?????文件???????1031??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\gam_rhs_state_bellman.m

?????文件???????2785??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\gam_script.m

?????文件???????4302??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\iter_poly_gw_inplace.m

?????文件???????4500??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\iter_poly_gw_not_inplace.m

?????文件???????2290??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\jcr_example.m

?????文件???????2679??2010-09-28?17:16??suntton強化學習書籍代碼\Chapter?4?（Dynamic?Programming）\jcr_policy_evaluation.m

............此處省略94個文件信息