cpprb 8.4.4

ReplayBuffer for Reinforcement Learning written by C++ and Cython

Overview

cpprb is a python (CPython) module providing replay buffer classes for reinforcement learning.

Major target users are researchers and library developers.

You can build your own reinforcement learning algorithms together with your favorite deep learning library (e.g. TensorFlow, PyTorch).

cpprb forcuses speed, flexibility, and memory efficiency.

By utilizing Cython, complicated calculations (e.g. segment tree for prioritized experience replay) are offloaded onto C++. (The name cpprb comes from "C++ Replay Buffer".)

In terms of API, initially cpprb referred to OpenAI Baselines' implementation. In the current version, cpprb has much more flexibility. Any NumPy compatible types of any numbers of values can be stored (as long as memory capacity is sufficient). For example, you can store the next action and the next next observation, too.

Installation

cpprb requires following softwares before installation.

• C++17 compiler (for installation from source)
  • GCC (maybe 7.2 and newer)
  • Visual Studio (2017 Enterprise is fine)
• Python 3
• pip

Cuurently, clang, which is a default Xcode C/C++ compiler at Apple macOS, cannot compile cpprb.

If you are macOS user, you need to install GCC and set environment values of CC and CXX to g++, or just use virtual environment (e.g. Docker).

Step by step installation is described here.

Additionally, here are user's good feedbacks for installation at macOS and Ubuntu. (Thanks!)

Install from PyPI (Recommended)

The following command installs cpprb together with other dependancies.

pip install cpprb

Depending on your environment, you might need sudo or --user flag for installation.

On supported platflorms (Linux x86-64 and Windows amd64), binary packages are hosted on PyPI can be used, so that you don't need C++ compiler.

If you have trouble to install from binary, you can fall back to source installation to passk --no-binary option to the above pip command.

Currently, no other platforms, such as macOS, and 32bit or arm-architectured Linux and Windows, cannot install from binary, and need to compile by yourself. Please be patient, we will plan to support wider platforms in future.

Install from source code

First, download source code manually or clone the repository;

git clone https://gitlab.com/ymd_h/cpprb.git

Then you can install same way;

cd cpprb
pip install .

For this installation, you need to convert extended Python (.pyx) to C++ (.cpp) during installation, it takes longer time than installation from PyPI.

Usage

Here is a simple example for storing standard environment (aka. "obs", "act", "rew", "next_obs", and "done").

from cpprb import ReplayBuffer

buffer_size = 256
obs_shape = 3
act_dim = 1
rb = ReplayBuffer(buffer_size,
		  env_dict ={"obs": {"shape": obs_shape},
			     "act": {"shape": act_dim},
			     "rew": {},
			     "next_obs": {"shape": obs_shape},
			     "done": {}})

obs = np.ones(shape=(obs_shape))
act = np.ones(shape=(act_dim))
rew = 0
next_obs = np.ones(shape=(obs_shape))
done = 0

for i in range(500):
    rb.add(obs=obs,act=act,rew=rew,next_obs=next_obs,done=done)


batch_size = 32
sample = rb.sample(batch_size)
# sample is a dictionary whose keys are 'obs', 'act', 'rew', 'next_obs', and 'done'

Flexible environment values are defined by env_dict when buffer creation.

Since stored values have flexible name, you have to pass to ReplayBuffer.add member by keyword.

Features

cpprb provides buffer classes for building following algorithms.

Algorithms	cpprb class	Paper
Experience Replay	`ReplayBuffer`	[L. J. Lin](https://link.springer.com/article/10.1007/BF00992699)
Prioritized Experience Replay	`PrioritizedReplayBuffer`	[T. Schaul et. al.](https://arxiv.org/abs/1511.05952)
Multi-step Learning	`ReplayBuffer`, `PrioritizedReplayBuffer`

cpprb features and its usage are described at following pages:

• Flexible Environment
• Multi-step add
• Prioritized Experience Replay
• Nstep Experience Replay
• Memory Compression

Contributing to cpprb

Any contribution are very welcome!

Making Community Larger

Bigger commumity makes development more active and improve cpprb.

• Star this repository (and/or GitHub Mirror)
• Publish your code using cpprb
• Share this repository to your friend and/or followers.

Report Issue

When you have any problems or requests, you can check issues on GitLab.com. If you still cannot find any information, you can open your own issue.

Merge Request (Pull Request)

cpprb follows local rules:

• Branch Name
  • "HotFix_***" for bug fix
  • "Feature_***" for new feature implementation
• docstring
  • Must for external API
  • Numpy Style
• Unit Test
  • Put test code under "test/" directory
  • Can test by python -m unittest <Your Test Code> command
  • Continuous Integration on GitLab CI configured by .gitlab-ci.yaml
• Open an issue and associate it to Merge Request

Step by step instruction for beginners is described at here.

Links

cpprb sites

• Project Site
  • Class Reference
  • Unit Test Coverage
• Main Repository
• Github Mirror
• cpprb on PyPI

cpprb users' repositories

• keiohta/TF2RL: TensorFlow2.0 Reinforcement Learning

Lisence

cpprb is available under MIT lisence.