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
Option | Description | Default |
---|---|---|
--algo ALGO | RL algorithm to use | REQUIRED |
--continue_training | Continue training from last checkpoint | False |
--model MODEL | Continue training from specific checkpoint |
Examples
See the Reinforcement Learning Workflow guide for detailed examples.