Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

srb agent train — Train Agent

The srb agent train command allows you to train Reinforcement Learning (RL) agents on Space Robotics Bench environments.

Usage

srb agent train --algo ALGO --env ENV_ID [options]

Options | Shared Agent Options

OptionDescriptionDefault
--algo ALGORL algorithm to useREQUIRED
--continue_trainingContinue training from last checkpointFalse
--model MODELContinue training from specific checkpoint

Examples

See the Reinforcement Learning Workflow guide for detailed examples.