| _version_ | 1866901745419943936 |
|---|---|
| author | Mahdi, Zrng |
| author_facet | Mahdi, Zrng |
| contents | <p><p>This work introduces and proposes a novel, bio-inspired paradigm for robotic learning. We present the conceptual framework for a hierarchical system that combines a large Vision-Language Model (VLM) as a high-level semantic evaluator with a distributed, low-level "Cell Assembly" motor cortex. The core of our contribution is the detailed formulation of a Reinforcement Learning from AI Feedback (RLAIF) loop for complex robotic tasks, such as humanoid locomotion.</p></p> <p><p>The proposed Cell Assembly, composed of a large set of simple, independent binary-like cells, generates actions. A VLM (e.g., LLaVA-1.5 7B) would then visually observe the outcome of these actions and provide a qualitative reward signal based on an abstract goal (e.g., "stand upright"). This feedback would be used to update the parameters of the cellular network via a policy gradient algorithm, as detailed in our provided mathematical formulation and pseudocode.</p></p> <p><p>This research serves as a theoretical foundation for creating more autonomous and adaptive learning agents, shifting the paradigm from manually engineered rewards to AI-driven "education," and from monolithic architectures to robust, hardware-inspired cellular systems. The core scientific documents outlining this framework are available at the project's GitHub repository: https://github.com/zorino96/VLM-Robot-Director</p></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17203749 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | RLAIF: A Conceptual Framework for a Bio-Inspired Cellular Architecture for Robot Learning Mahdi, Zrng Embodied AI, RLAIF, Reinforcement Learning from AI Feedback, VLM, Robotics, Bio-Inspired AI, Cellular Architecture, Conceptual Framework, Theoretical AI, Humanoid Control, LLaVA <p><p>This work introduces and proposes a novel, bio-inspired paradigm for robotic learning. We present the conceptual framework for a hierarchical system that combines a large Vision-Language Model (VLM) as a high-level semantic evaluator with a distributed, low-level "Cell Assembly" motor cortex. The core of our contribution is the detailed formulation of a Reinforcement Learning from AI Feedback (RLAIF) loop for complex robotic tasks, such as humanoid locomotion.</p></p> <p><p>The proposed Cell Assembly, composed of a large set of simple, independent binary-like cells, generates actions. A VLM (e.g., LLaVA-1.5 7B) would then visually observe the outcome of these actions and provide a qualitative reward signal based on an abstract goal (e.g., "stand upright"). This feedback would be used to update the parameters of the cellular network via a policy gradient algorithm, as detailed in our provided mathematical formulation and pseudocode.</p></p> <p><p>This research serves as a theoretical foundation for creating more autonomous and adaptive learning agents, shifting the paradigm from manually engineered rewards to AI-driven "education," and from monolithic architectures to robust, hardware-inspired cellular systems. The core scientific documents outlining this framework are available at the project's GitHub repository: https://github.com/zorino96/VLM-Robot-Director</p></p> |
| title | RLAIF: A Conceptual Framework for a Bio-Inspired Cellular Architecture for Robot Learning |
| topic | Embodied AI, RLAIF, Reinforcement Learning from AI Feedback, VLM, Robotics, Bio-Inspired AI, Cellular Architecture, Conceptual Framework, Theoretical AI, Humanoid Control, LLaVA |
| url | https://doi.org/10.5281/zenodo.17203749 |