digitado

Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We relate plasticity to the empirical Neural Tangent Kernel, and identify dynamical isometry (the condition that layer-wise Jacobian singular values remain close to one) as a key mechanism for preserving plasticity in continual learning. We revisit a class of networks that are almost-everywhere isometric while remaining universal Lipschitz function approximators, demonstrating that near-dynamical isometry is compatible with expressive […]

Ver mais

Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric retrieval-based imitation learning approach can alleviate this challenge. We present Difference-Aware Retrieval Policies for Imitation Learning (DARP), a semi-parametric retrieval-based imitation learning approach that addresses this limitation by reparameterizing the imitation learning problem in terms of local neighborhood structure rather than direct state-to-action mappings. Instead of […]

Ver mais

Responses to perturbations are key to understanding physical systems. The ability to contrast such responses by comparing how a system reacts under slightly different conditions provides a mechanism for learning. Here, we introduce Perturbative Contrastive Physical Learning (PCPL), a general framework in which learning emerges from measurable contrasts between physical states produced by controlled changes to inputs, boundary conditions, parameters, or interpreter functions. PCPL unifies and extends prior approaches: Equilibrium Propagation is rooted in contrasts between free and […]

Ver mais

Ok so I‘ve been watching a bunch of videos about people using reinforcement learning to teach their agents(?) to play games such as bowling or tag, but one that stood out to me was Yosh’s video on making an ai play the game trackmania, so I wanted to make a reinforcement learning algorithm to play Geometry Dash, since I feel like it shouldn’t be too hard, but I have no clue where to start, could anybody help/give me […]

Ver mais

We study feed-forward ReLU networks with fixed readout and quadratic loss. The aim is to rewrite gradient descent not primarily as a dynamics in weight space, but as a collective dynamics closed in terms of fields defined on the training-set space. For a single hidden layer, the weight variables can be eliminated from the activation dynamics, yielding a closed equation for the residuals governed by a collective kernel that factorizes into an input-geometric matrix and a dynamical co-activation […]

Ver mais

AI agent performance is not just a modeling problem; it is fundamentally a systems problem. A modern agent combines an LLM with a harness, software that mediates the LLM’s interaction with tools and manages the cycle of reasoning and feedback: you can think of the harness as the operating system around the model. As models improve, the performance bottleneck shifts from the model’s ability to reason to the harness’s ability to translate model intent into actions and reflect […]

Ver mais

Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that failure appears. We introduce Proxy Reward Internalization and Mechanistic Exploitation (PRIME), a learned capability to assess task correctness, predict proxy acceptance, and reason about exploitable proxy–gold gaps. In coding RL environments with exploitable pytest rewards, we measure PRIME through chain-of-thought monitoring, direct probes, and activation-level concept vectors. We […]

Ver mais