Safe-Multi-Agent-Robosuite

by chauncygu · indexed from github

Safe Multi-Agent Robosuite benchmark for safe multi-agent reinforcement learning research.

Safe Multi-Agent Robosuite is an extension of Robosuite . We split the control over a robot across multiple controllers of its joints---one or more per controller. For example, the Lift task comes with 3 variants: 2 four-dimensional agents (2x4 Lift), 4 two-dimensional agents (4x2 Lift), and 8 one-dimensional agents (8x1 Lift). (This repository is under actively development. We appreciate any constructive comments and suggestions)

AI agentIndexed · not connecteddata
Use this agent →

⚡ How to use Safe-Multi-Agent-Robosuite

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/chauncygu-safe-multi-agent-robosuite

Capabilities

research

Do you own Safe-Multi-Agent-Robosuite?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.