parl 2.2.1


Reinforcement Learning Framework

Reinforcement Learning Framework

Stars: 3036, Watchers: 3036, Forks: 812, Open Issues: 117

The PaddlePaddle/PARL repo was created 5 years ago and the last code push was 3 days ago.
The project is very popular with an impressive 3036 github stars!

How to Install parl

You can install parl using pip

pip install parl

or add it to a project with poetry

poetry add parl

Package Details

GitHub Repo


No  parl  pypi packages just yet.


A list of common parl errors.

Code Examples

Here are some parl code examples and snippets.

GitHub Issues

The parl package has 117 open issues on GitHub

  • train.py导入parl时报错怎么解决
  • fix core dump on aarch64
  • Bump paddlepaddle from 1.8.5 to 2.5.0 in /.teamcity
  • Bump paddlepaddle from 2.4.2 to 2.5.0 in /docs
  • Bump paddlepaddle from 2.2.0 to 2.5.0 in /examples/tutorials/parl2_dygraph
  • Bump paddlepaddle from 2.0.0 to 2.5.0 in /examples/AlphaZero
  • Bump paddlepaddle from 1.8.5 to 2.5.0 in /examples/tutorials
  • import parl时报错RuntimeError问题
  • ES单机多卡训练报错 ERR [xparl] lost connection with a job
  • 运用动态图的DDPG代码model部分报错ValueError: (InvalidArgument) The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [48, 8], input[1]'s shape = [48, 1, 2].
  • 运行后self.build_program()报错
  • Bump grpcio from 1.37.0 to 1.53.0
  • ppo_mujocov2
  • 使用Paddle Custom NPU训练SAC一段时间后reward一直不变
  • AttributeError: Can't pickle local object 'check_installed_framework.<locals>.check'

See more issues on GitHub

Related Packages & Articles

rlcard 1.2.0

A Toolkit for Reinforcement Learning in Card Games

parmap 1.6.0

map and starmap implementations passing additional arguments and parallelizing if possible