gaspersic/Gymnasium
1
0
Fork 0
mirror of https://github.com/Farama-Foundation/Gymnasium.git synced 2025-08-27 16:57:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Clean some docstrings (#1854)

Browse Source 
* add type of argument

* fix typos

* split lines for formatting

* reformat string, add ellipsis, remove r string

* make docstring stylistically consistent

* make docstrings a little more elaboratet

* reduce by 1 space

* make line wrap 120

* remove unnecessary line

* add returns to docstring

* add docstring, make code more pep8 and delete some unused print functions

* more pep8

* file docstring instead of comments

* delete unused variables, add file docstring and add some pep8 spring cleaning

* add file docstring, fix typos and add some pep8 correections

Co-authored-by: Dan <daniel.timbrell@ing.com>
This commit is contained in:
Dan Timbrell
2020-04-24 23:10:27 +02:00
committed by GitHub
parent f2c9793eb7
commit 3bd5ef71c2
7 changed files with 360 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
examples/agents/cem.py
View File

@@ -11,12 +11,20 @@ def cem(f, th_mean, batch_size, n_iter, elite_frac, initial_std=1.0):
"""
Generic implementation of the cross-entropy method for maximizing a black-box function
f: a function mapping from vector -> scalar
th_mean: initial mean over input distribution
batch_size: number of samples of theta to evaluate per batch
n_iter: number of batches
elite_frac: each batch, select this fraction of the top-performing samples
initial_std: initial standard deviation over parameter vectors
Args:
f: a function mapping from vector -> scalar
th_mean (np.array): initial mean over input distribution
batch_size (int): number of samples of theta to evaluate per batch
n_iter (int): number of batches
elite_frac (float): each batch, select this fraction of the top-performing samples
initial_std (float): initial standard deviation over parameter vectors
returns:
A generator of dicts. Subsequent dicts correspond to iterations of CEM algorithm.
The dicts contain the following values:
'ys' : numpy array with values of function evaluated at current population
'ys_mean': mean value of function over current population
'theta_mean': mean value of the parameter vector over current population
"""
n_elite = int(np.round(batch_size*elite_frac))
th_std = np.ones_like(th_mean) * initial_std