Reinforcement Learning Coach

Coach is a python framework which models the interaction between an agent and an environment in a modular way. With Coach, it is possible to model an agent by combining various building blocks, and training the agent on multiple environments. The available environments allow testing the agent in different fields such as robotics, autonomous driving, games and more. It exposes a set of easy-to-use APIs for experimenting with new RL algorithms, and allows simple integration of new environments to solve. Coach collects statistics from the training process and supports advanced visualization techniques for debugging the agent being trained.

Blog posts from the Intel® AI website:

• Release 0.8.0 (initial release)

• Release 0.9.0

• Release 0.10.0

• Release 0.11.0

• Release 0.12.0

• Release 1.0.0 (current release)

You can find more details in the GitHub repository.

Intro

• Usage
• Usage - Distributed Coach
• Features
  • Algorithms
  • Environments
  • Benchmarks
  • Batch Reinforcement Learning
• Selecting an Algorithm
• Coach Dashboard

Design

• Control Flow
• Network Design
• Distributed Coach - Horizontal Scale-Out

Contributing

• Adding a New Agent
• Adding a New Environment

Components

• Agents
• Architectures
• Data Stores
• Environments
• Exploration Policies
• Filters
• Memories
• Memory Backends
• Orchestrators
• Core Types
• Spaces
• Additional Parameters