Apps · PROJECT NOTES
AgentGym
A common client/server interface for interactive agent environments, accompanied by evaluation tasks, trajectories and agent-development workflows.
What can you do with it?
Use consistent reset, observation and action calls across environments and reuse trajectories for evaluation or behavioral training.
What should you know before using it?
Installing agentenv alone does not install every environment: each server has its own dependencies and data. Integrated WebArena, games and other environments overlap existing projects. AgentGym-RL is a companion training stack. Framework code is MIT; upstream components retain their terms.
What is verified here?
This entry was reviewed against original project material. We have not independently run the software or reproduced its results. AI-development claims are author-reported; check upstream for current versions, setup requirements, and licenses.
- Resource type
- Environment framework
- Provenance
- Development provenance not established
- Reviewed
- Platforms
- Consult upstream documentation