arXiv AI
Jul 23
Sophisticated Policies from Epistemic Priors
arXiv:2607. 19518v1 Announce Type: new Abstract: Sophisticated Inference is a variant of active inference often associated with recursive belief modeling and tree search.
What Type of Inference is Active Inference?
arXiv:2606. 04935v1 Announce Type: new Abstract: Active inference casts decision-making as inference, with the Expected Free Energy (EFE) unifying goal-directed and information-seeking behavior.
Related stories
arXiv AI
Jul 23
Active Inference as a Convex Markov Decision Process
arXiv:2607. 20152v1 Announce Type: cross Abstract: Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principle.
arXiv Machine Learning
Aug 17
Expected Free Energy-based Informative Path Planning for Robotic Mars Exploration
arXiv:2608. 14466v1 Announce Type: cross Abstract: An autonomous robot efficiently exploring an unknown environment, such as looking for water sources on Mars, faces two simultaneous demands: building an accurate information map while quickly finding the regions of greatest value, and paying for every meter of travel and the cost of every measurement it takes.
arXiv AI
Jun 9
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
arXiv:2606. 09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM).
arXiv AI
Jul 16
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models
arXiv:2607. 13612v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models, yet they are usually justified by empirical performance rather than a normative principle.
arXiv AI
Aug 19
Expected free energy as an information constraint on the Bethe Lagrangian
The paper introduces a Bethe Lagrangian formulation of expected free energy (EFE) that preserves a Kullback–Leibler structure, enabling message‑passing inference. By imposing an information constraint—requiring the mutual information between future observations, states, and parameters given actions to be at least the entropy of the goal prior—the authors recover the standard EFE solution at a specific Karush‑Kuhn‑Tucker multiplier. They analyze how varying this multiplier transitions the agent’s epistemic drive through inactive, interior, and saturated regimes, and benchmark the constrained Bethe agent against EFE and Q‑MDP on three tasks.
arXiv Machine Learning
Sep 4
Latent Energy Action Planning with World Models
Latent Energy Action Planning (LEAP) is a new method that treats the entire action horizon as a differentiable variable and optimizes it using a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal‑window state energy, ensuring that the predicted terminal latent and decoder‑predicted terminal descriptor align with the goal. Using a frozen goal‑conditioned proposal, a quasi‑Newton solver, and post‑optimization projection, LEAP improves mean success from 77.5% to 94.8% across four control domains while keeping the LeWM representation frozen.
Hugging Face Trending Papers
Sep 3
Latent Energy Action Planning with World Models
Latent Energy Action Planning (LEAP) improves model predictive control by treating the entire action horizon as a differentiable variable and optimizing it using a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal-window state energy, ensuring both the predicted terminal latent and the decoder-predicted terminal descriptor align with the goal. In four control domains, LEAP raises mean success from 77.5% (LeWM+CEM) to 94.8%, a 17.3‑percentage‑point improvement while keeping the frozen LeWM representation.
arXiv Machine Learning
Aug 18
MDP Planning as Policy Inference
arXiv:2602. 17375v3 Announce Type: replace Abstract: We formulate episodic Markov decision process (MDP) planning as Bayesian inference over policies.
arXiv AI
3d ago
Belief-Based Maximum Occupancy Principle and Active Inference
arXiv:2609.39342v1 Announce Type: cross Abstract: Intrinsic motivation plays a central role in adaptive and goal-directed behavior by conferring agents reward-independent objectives and biases useful...
arXiv Computer Vision
Aug 26
LeFlow: Generative Latent Flow Planning for World Models
arXiv:2608.24855v1 Announce Type: new Abstract: Latent world models are inherently strong encoders that transform image pixel to latent embedding, yet existing world models still rely on online traje...
arXiv AI
Aug 21
Active Inference as Context Acquisition for AI Agents
arXiv:2608. 19202v1 Announce Type: new Abstract: Interactive AI agents must acquire the right context as efficiently as possible.