The Python Component System (PCS) is an API and CLI for building, running, and sharing Python code. AgentOS is a set of libraries built on top of PCS that make it easy to build, run, and share agents that use Reinforcement Learning.
This updates the default agent (created by agentos init) to use AgentRun so that it's compatible with the web frontend. This is part of a larger push to automatically populate the web with data for testing and demo purposes.
This also updates example_agent/random to match the default agent.
Demo:
# Start the local web server in a separate tab
# Clear the local DB by visiting http://localhost:8000/empty_database in your browser
mkdir demo
cd demo
agentos init .
agentos run agent
USE_LOCAL_SERVER=True agentos publish <agent run ID printed out after previous previous command>
# Now visit http://localhost:8000 and see the result of your run
The leaderboard will show something like the following after running the demo script:
This updates the default agent (created by
agentos init) to useAgentRunso that it's compatible with the web frontend. This is part of a larger push to automatically populate the web with data for testing and demo purposes.This also updates
example_agent/randomto match the default agent.Demo:
The leaderboard will show something like the following after running the demo script: