# -*- coding: utf-8 -*- import wx import wx.lib import wx.lib.plot as plot import math import random as rnd import numpy as np import copy # import pickle # Steps looking back STATE_NUM = 2 # State STATE_NUM = 2 NUM_EYES = 9 STATE_DIM = NUM_EYES * 3 * 2 class SState(object): def __init__(self): self.seq = np.ones((STATE_NUM, NUM_EYES*3), dtype=np.float32) def push_s(self, state): self.seq[1:STATE_
![Action value Actor-Critic型Policy Gradientによる連続値動作の強化学習 - Qiita](https://cdn-ak-scissors.b.st-hatena.com/image/square/bb6b0dcf6df07c4043d3c6520d89284c214d4338/height=288;version=1;width=512/https%3A%2F%2Fqiita-user-contents.imgix.net%2Fhttps%253A%252F%252Fcdn.qiita.com%252Fassets%252Fpublic%252Farticle-ogp-background-412672c5f0600ab9a64263b751f1bc81.png%3Fixlib%3Drb-4.0.0%26w%3D1200%26mark64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZ3PTk3MiZoPTM3OCZ0eHQ9QWN0aW9uJTIwdmFsdWUlMjBBY3Rvci1Dcml0aWMlRTUlOUUlOEJQb2xpY3klMjBHcmFkaWVudCVFMyU4MSVBQiVFMyU4MiU4OCVFMyU4MiU4QiVFOSU4MCVBMyVFNyVCNiU5QSVFNSU4MCVBNCVFNSU4QiU5NSVFNCVCRCU5QyVFMyU4MSVBRSVFNSVCQyVCNyVFNSU4QyU5NiVFNSVBRCVBNiVFNyVCRiU5MiZ0eHQtYWxpZ249bGVmdCUyQ3RvcCZ0eHQtY29sb3I9JTIzMjEyMTIxJnR4dC1mb250PUhpcmFnaW5vJTIwU2FucyUyMFc2JnR4dC1zaXplPTU2JnM9NzE5YmE1NmY0ZDE4NzVjOWQ4Mjk0OTdmMTkwNWU1NjM%26mark-x%3D142%26mark-y%3D57%26blend64%3DaHR0cHM6Ly9xaWl0YS11c2VyLWNvbnRlbnRzLmltZ2l4Lm5ldC9-dGV4dD9peGxpYj1yYi00LjAuMCZoPTc2Jnc9NzcwJnR4dD0lNDBjaGFjaGF5JnR4dC1jb2xvcj0lMjMyMTIxMjEmdHh0LWZvbnQ9SGlyYWdpbm8lMjBTYW5zJTIwVzYmdHh0LXNpemU9MzYmdHh0LWFsaWduPWxlZnQlMkN0b3Amcz0xNzNmZThlYzU5OTY2ODU2YTY2MDBmNmJiZTY1M2Q0Mw%26blend-x%3D142%26blend-y%3D486%26blend-mode%3Dnormal%26s%3Dbeef10a887d8d1dc15adee5b53ad0972)