Evolving Programmatic Skill Networks
This addresses the challenge of building adaptable and reusable skill libraries for embodied AI agents in open-ended environments, representing a novel method rather than an incremental improvement.
The paper tackles the problem of continual skill acquisition in open-ended embodied environments by introducing the Programmatic Skill Network (PSN), a framework that uses executable symbolic programs to construct, refine, and reuse skills, resulting in robust skill reuse, rapid adaptation, and strong generalization across tasks in MineDojo and Crafter.
We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)REFLECT for structured fault localization over skill compositions, (2) progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3) canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.\footnote{We plan to open-source the code.