ReplayBuffer for Reinforcement Learning written by C++
Project description
cpprb is a python package written by C++. The package provides replay buffer classes for reinforcement learning.
Complicated calculation (e.g. Segment Tree) are offloaded onto C++ which must be much faster than Python.
Internal C++ classes and corresponding Python wrapper classes share memory by implementing buffer protocol on cython to avoid overhead of copying large data.
This package requires C++17 compatible compiler to build.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
cpprb-7.7.0.tar.gz
(227.6 kB
view details)
File details
Details for the file cpprb-7.7.0.tar.gz.
File metadata
- Download URL: cpprb-7.7.0.tar.gz
- Upload date:
- Size: 227.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.2 pkginfo/1.4.2 requests/2.21.0 setuptools/41.0.0 requests-toolbelt/0.8.0 tqdm/4.31.1 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e9f4b08b1dbed8b2a76e3986a2c5373df75e5b936fac60cb1595becaec51a5a3
|
|
| MD5 |
9e9ebb7f5c175f20b87d9ee3db98e2a6
|
|
| BLAKE2b-256 |
e64273a72957c21f8783e47d43898741cd2b4e83a7f5e90148d79b6773bb0e36
|
