Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
We address the problem of fine-tuning pre-trained generative policies with reinforcement learning (RL) while preserving the multimodality of their action distributions. Existing methods for RL fine-tuning of generative policies (e.g., diffusion policies) improve task performance but often collapse diverse behaviors into a single reward-maximizing mode. To mitigate this issue, we propose an unsupervised mode discovery framework that uncovers latent behavioral modes within generative policies. The discovered modes enable the use of mutual information as an intrinsic reward, regularizing RL fine-tuning to enhance task success while maintaining behavioral diversity. Experiments on robotic manipulation tasks demonstrate that our method consistently outperforms conventional fine-tuning approaches, achieving higher success rates and preserving richer multimodal action distributions.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
BehaviorVLM: Unified Finetuning-Free Behavioral Understanding with Vision-Language Reasoning
Understanding freely moving animal behavior is central to neuroscience, where pose estimation and behavioral understanding form the foundation for linking neural activity to natural actions. Yet both tasks still depend h…
Video CaptioningPose EstimationFine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
Autism spectrum disorder (ASD) affects 1 in 31 US children, yet median age at diagnosis exceeds four years. Artificial intelligence pipelines that provide quantified diagnosis using easy to access observational data (e.g…
Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment
Fine-tuning LLMs on narrowly harmful datasets can lead to behavior that is broadly misaligned with respect to human values. To understand when and how this emergent misalignment occurs, we develop a comprehensive framewo…
Change DetectionMMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Seman…
Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint
Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of segments, delivery of messages to users …
Stochastic Optimization