PARL Logo
latest

Overview

  • Features
  • Abstractions
  • Parallelization

Installation

  • Installation

Tutorial

  • Getting Started
  • Model, Algorithm, Agent
  • Create Customized Algorithms
  • Save and Restore Parameters
  • Visualization Tool
  • CSV Logger

High-quality Implementations

  • Policy Gradient
  • DQN
  • DDPG
  • DDQN
  • OAC
  • A2C
  • TD3
  • QMIX
  • SAC
  • PPO
  • MADDPG

Parallel Training

  • Overview
  • Xparl Usage
  • Recommended Practice
  • Recommended Practice(no_wait mode)
  • GPU Cluster
  • How to Debug
  • File Distribution
  • Serialization Acceleration (Not Necessary)

APIs

  • parl.Model
  • parl.Algorithm
  • parl.Agent
  • parl.remote_class
  • parl.connect

Frequently Asked Questions

  • xparl questions
  • RL questions

EvoKit

  • Overview
  • minimal example
  • Example for Online Products
PARL
  • Docs »
  • Overview: module code

All modules for which code is available

  • parl.algorithms.fluid.impala.impala
  • parl.algorithms.paddle.a2c
  • parl.algorithms.paddle.ddpg
  • parl.algorithms.paddle.ddqn
  • parl.algorithms.paddle.dqn
  • parl.algorithms.paddle.maddpg
  • parl.algorithms.paddle.oac
  • parl.algorithms.paddle.policy_gradient
  • parl.algorithms.paddle.ppo
  • parl.algorithms.paddle.qmix
  • parl.algorithms.paddle.sac
  • parl.algorithms.paddle.td3
  • parl.core.paddle.agent
  • parl.core.paddle.algorithm
  • parl.core.paddle.model
  • parl.remote.client
  • parl.remote.remote_decorator

© Copyright 2021, nlp-ol@baidu.com Revision 1fc50bf5.

Built with Sphinx using a theme provided by Read the Docs.