A simple wrapper to analyse and visualise reinforcement learning agents' behaviour in the environment.
Project description
Visrl
Visrl (pronounced "visceral") is a simple wrapper to analyse and visualise reinforcement learning agents' behaviour in the environment.
Install
pip install visrl
Usage
import visrl
Features:
- Key-to-action: Set action hotkeys
- Step: Take actions 1 step at a time
- Continue: Return control to agent
- Speed up/slow down: Control frame rate
- Values: Show all relevant values and plot history
- Breakpoint: Run until condition involving values
- Playback/record: Show past frames and actions
- Save point: Save environment state to restart from
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
visrl-0.1.2.tar.gz
(4.8 kB
view hashes)
