arXiv:2608. 17167v1 Announce Type: cross Abstract: Active inference selects actions by minimising an expected free energy functional over predicted futures.
arXiv:2607. 16858v1 Announce Type: cross Abstract: Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surprise.
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:2607. 19518v1 Announce Type: new Abstract: Sophisticated Inference is a variant of active inference often associated with recursive belief modeling and tree search.
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.
arXiv:2608. 15922v1 Announce Type: cross Abstract: We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph.
arXiv:2509. 20114v3 Announce Type: replace Abstract: We study \emph{online episodic Constrained Markov Decision Processes} (CMDPs) under both stochastic and adversarial constraints.
arXiv:2605. 08446v3 Announce Type: replace Abstract: Bayesian neural networks are typically trained against the evidence lower bound (ELBO), whose Jensen gap closes only when the variational posterior is exact.
arXiv:2604. 21407v2 Announce Type: replace Abstract: When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that very likely does not contain the target.
arXiv:2607. 16981v1 Announce Type: new Abstract: An agent acting under partial observability must decide when to gather information and which observations are worth their cost.
arXiv:2602. 13421v2 Announce Type: replace-cross Abstract: Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available.
arXiv:2605. 26078v3 Announce Type: replace Abstract: Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions.
arXiv:2607. 17316v1 Announce Type: new Abstract: The softmax policy $\pi(a \mid s) \propto \exp(\beta Q(s,a))$ is the default model of stochastic choice in reinforcement learning (RL).