Technology53m ago1 min read
Google AI Releases EnvHarness to Adapt Static Agent Environments
Google Cloud AI Research, Washington University in St. Louis, and UNC Chapel Hill released EnvHarness, a programmable layer that adapts static agent environments to the policy training on them. The system wraps existing environments in plug-in components that alter episode starts, actions, and observations while preserving the original simulator and verifier. Across five benchmarks in four domains, skills mined this way gain up to 9.0 points on held-out tasks with 9.8% fewer execution steps.