MLINFO COLLECTION
Robot foundation models may generalize across tasks and embodiments, but their actions still depend on sensors that can fail. When the policy is frozen or inaccessible, can an external monitor…
In this paper, we introduce a model-based boosting approach for fitting structured additive distributional copula regression models for bivariate responses, with particular emphasis on jointly…
It is well established that some animals, such as sea turtles, sense the Earth's magnetic field and use it as a primary cue for long-distance navigation across the vast and featureless ocean. This…
When allocating indivisible goods, the maximum Nash welfare rule is known to be the unique welfarist rule satisfying envy-freeness up to one good. We strengthen this characterization by showing that…
We consider $T$ repeated second-price auctions across $n$ pacing bidders with i.i.d. item arrivals, and show that it is computationally impossible for all bidders to achieve no-regret simultaneously…
Miner extractable value (MEV) poses a persistent challenge for blockchain ecosystems. It arises from the fact that a block builder can exploit its unilateral control over transaction inclusion and…
The adaptive clinching auction of Dobzinski, Lavi, and Nisan (FOCS'08) is a cornerstone of mechanism design with budget-constrained bidders, and it has since inspired a broad range of extensions to…
We present CPG-ENN, a trainable quadruped locomotion framework that combines explicit neural coordination with learned motion realization. A symmetry-based eight-neuron central pattern generator…
The inefficiency of decentralized resource allocation is classically measured by the Price of Anarchy (PoA) and the Price of Stability (PoS). The most widely studied and foundational class of these…
AI agents must decide when another search is worth its cost. Answer-success probabilities capture question difficulty, while this decision requires estimating the additional benefit of search.
このリポジトリでは、LLMベースのエージェントアプリケーションのための強化学習の橋渡しを提供しています。
Replicator dynamics, the central model of evolutionary game theory, describe populations evolving under selection and agents learning by trial and error. They also admit a third use: continuous-time…
Computing local-level variable importance (VI) is critical for understanding machine learning models. Local permutation-based VI metrics offer a simple yet powerful approach, measuring how much a…
Dealing with climate change requires that all countries engage in costly efforts to reduce their emissions. Reaching this objective has so far been elusive because it is in the best interest of each…
The MOEA/D is one of the most successful multi-objective evolutionary algorithms. It operates by decomposing the optimization problem into single-objective subproblems, which are then solved in a…
Lightning routing nodes lend their channel balance for a posted fee. Operators' tools move that fee with the balance around a hand-set level, and which part of the fee drives revenue is unclear.
We study welfare maximization in a contract model with $m$ principals who privately value a public project's success and $n$ agents whose costly effort is unobservable. Contracts induce truthful…
Well-documented failure modes of machine learning (ML) systems, including bias, toxicity, hallucination, and leakage of sensitive information, has driven the rise of machine unlearning (MU). Most…
Simulation-based inference often encodes observations $Y$ into a fixed-dimensional summary $S$, with the posterior conditioning only on $S$. While exact preservation often requires infinite…
Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which connects paired tests of a frozen acceptance rule…
Many high-stakes collective problems, e.g., climate mitigation and pandemic response, share a structure in which risk materializes unless a group threshold is met. This threshold is often uncertain,…
Connectomes now map the neurons and synapses of an adult fly's brain and nerve cord, but how much of behaviour follows from the wiring is unknown. Here we turn one such connectome into a spiking…
Permissionless blockchains use transaction fee mechanisms to allocate the resources that transactions consume, such as execution, data bandwidth, and state creation. Recent blockchain designs explore…
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/