paper-with-me

홈 › Papers

Active Inference with Reusable State-Dependent Value Profiles

2025-12-03 · Jacob Poschl arxiv

Adaptive behavior in volatile environments requires agents to switch among value-control regimes across latent contexts, but maintaining separate preferences, policy biases, and action-confidence parameters for every situation is intractable. We introduce value profiles: a small set of reusable bundles of value-related parameters (outcome preferences, policy priors, and policy precision) assigned to hidden states in a generative model. As posterior beliefs over states evolve trial by trial, effective control parameters arise via belief-weighted mixing, enabling state-conditional strategy recruitment without requiring independent parameters for each context. We evaluate this framework in probabilistic reversal learning, comparing static-precision, entropy-coupled dynamic-precision, and profile-based models using cross-validated log-likelihood and information criteria. Model comparison favors the profile-based model over simpler alternatives (about 100-point AIC differences), and parameter-recovery analyses support structural identifiability even when context must be inferred from noisy observations. Model-based inference further suggests that adaptive control in this task is driven primarily by modulation of policy priors rather than policy precision, with gradual belief-dependent profile recruitment consistent with state-conditional (not purely uncertainty-driven) control. Overall, reusable value profiles provide a tractable computational account of belief-conditioned value control in volatile environments and yield testable signatures of belief-dependent control and behavioral flexibility.

📄 PDF Abstract BibTeX arXiv:2512.11829

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs

2026-07-28 · Yu Hao, Jinxuan Cai, Qi Zhang, Yawen Li 외 arxiv

Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. However, existing trajectory-to-skill methods often produce flat coll…

Active Inference as a Convex Markov Decision Process

2026-07-22 · Nikola Milosevic, Nicolás Hinrichs, Nico Scherf arxiv

Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle. We frame AIF as policy optimization a…

Reinforcement Learning

ReadOnce Transformers: Reusable Representations of Text for Transformers

2020-10-24 · ACL 2021 5 · Shih-ting Lin, Ashish Sabharwal, Tushar Khot

We present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. The resulting representation i…

Document Summarization

ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

2026-08-20 · Yichu Fang, Sitong Wei, Haozhe Hu, Xiaoyu Shen arxiv

Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states. We introduce…

Sophisticated Inference

2020-06-07 · Karl Friston, Lancelot Da Costa, Danijar Hafner, Casper Hesp 외

Active inference offers a first principle account of sentient behaviour, from which special and important cases can be derived, e.g., reinforcement learning, active learning, Bayes optimal inference, Bayes optimal design…

Active LearningcounterfactualForm