Skip to content

Update docs/spinningup/rl_intro.rst #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
freemedom wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

Update docs/spinningup/rl_intro.rst #4

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f40c642
Update rl_intro.rst
freemedom May 20, 2023
99283bc
Update rl_intro.rst
freemedom May 20, 2023
cd445ba
Update rl_intro.rst
freemedom May 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions docs/spinningup/rl_intro.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,10 +193,10 @@
.. _`tf.random_normal`: https://www.tensorflow.org/api_docs/python/tf/random_normal
.. _`tf.distributions.Normal`: https://www.tensorflow.org/api_docs/python/tf/distributions/Normal

运动轨迹
行动轨迹
------------

运动轨迹 :math:`\tau` 指的是状态和行动的序列。
行动轨迹 :math:`\tau` 指的是状态和行动的序列。

.. math::

Expand All @@ -214,7 +214,7 @@

s_{t+1} = f(s_t, a_t)

而可以是随机的：
也可以是随机的：

.. math::

Expand Down Expand Up @@ -265,9 +265,9 @@

无论选择哪种方式衡量收益（:math:`T` 步累计奖赏或者 :math:`\gamma` 折扣奖励），无论选择哪种策略，强化学习的目标都是选择一种策略从而最大化 **预期收益**。

讨论预期收益之前，我们先讨论下行动轨迹的可能性分布。
讨论预期收益之前，我们先讨论下行动轨迹的概率分布。

我们假设环境转换和策略都是随机的。这种情况下， :math:`T` 步 行动轨迹是：
我们假设环境转换和策略都是随机的。这种情况下， :math:`T` 步 行动轨迹的概率是：

.. math::

Expand Down