latest

Installation
A First Example
Maze - Step by Step
API Documentation

Workflow

Training
Rollouts
Collecting and Visualizing Rollouts
Imitation Learning and Fine-Tuning

Policy and Value Networks

Introducing the Perception Module
Action Spaces and Distributions
Working with Template Models
Working with Custom Models

Trainers

Maze Trainers
Maze RLlib Runner

Concepts and Structure

Policies, Critics and Agents
Maze Environment Hierarchy
Maze Event System
Configuration with Hydra
Environment Rendering

Environment Customization

Customizing Core and Maze Envs
Customizing / Shaping Rewards
Environment Wrappers
Observation Pre-Processing
Observation Normalization

Best Practices and Tutorials

Tricks of the Trade
Structured Environments and Action Masking
Integrating an Existing Gym Environment
- Instantiating a Gym Environment as a Maze Environment
- Where to Go Next
Combining Maze with other RL Frameworks
Rollout and Training Examples

Logging

Tensorboard and Command Line Logging
Event and KPI Logging
Action Distribution Visualization
Observation Distribution Visualization

Scaling the Training Process

Runner Concept

Maze

»
API Documentation »
Trainers and Training Runners »
ESRolloutResult
Edit on GitHub

ESRolloutResult¶

class maze.train.trainers.es.distributed.es_distributed_rollouts.ESRolloutResult(is_eval: bool)¶: Result structure for distributed rollouts.

Next Previous

© Copyright 2021, EnliteAI GmbH. Revision 216c9e66.

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