Welcome to GenRL’s documentation!

Features

• Unified Trainer and Logging class: code reusability and high-level UI
• Ready-made algorithm implementations: ready-made implementations of popular RL algorithms.
• Extensive Benchmarking
• Environment implementations
• Heavy Encapsulation useful for new algorithms

Contents

User Guide

• Installation
  • PyPI Package
  • From Source
• About
  • Introduction
  • Policies and Values
  • Trainers and Loggers
  • Agent Encapsulation
  • Environments
• Tutorials
  • Bandit Tutorials
  • Classical
  • Deep RL Tutorials
  • Custom Policy Networks
  • Using A2C
  • Using Shared Parameters in Actor Critic Agents in GenRL
  • Vanilla Policy Gradient (VPG)
  • Saving and Loading Weights and Hyperparameters with GenRL

API

• Agents
  • A2C
  • DDPG
  • DQN
  • PPO1
  • VPG
  • TD3
  • SAC
  • Q-Learning
  • SARSA
  • Contextual Bandit
  • Multi-Armed Bandit
• Environments
  • Environments
  • Vectorized Envrionments
• Core
  • ActorCritic
  • Base
  • Buffers
  • Noise
  • Policies
  • RolloutStorage
  • Values
• Utilities
  • Logger
  • Utilities
  • Models
• Trainers
  • On-Policy Trainer
  • Off-Policy Trainer
  • Classical Trainer
  • Deep Contextual Bandit Trainer
  • Multi Armed Bandit Trainer
  • Base Trainer
• Common
  • Classical Common
  • Bandit Common