ctpolicy2varyingdamping.m

来自「approximate reinforcement learning」· M 代码 · 共 13 行

% Adhoc script to transfer a varying-damping model to a constant-damping datafile

clear all

% load grids, policy etc. from constant scenario
load navdata_ct_eps1e7_serial
clear qistats       % they might take a huge memory, and we don't need them in the resulting datafile
% we only need the model from the varying scenario
load navdata_2h_eps1e2_serial model

save ctpolicy_2hmodel