technocracy

arXiv:2604.04983v1 Announce Type: new Abstract: We present Territory Paint Wars, a minimal competitive multi-agent reinforcement learning environment implemented in Unity, and use it to systematically investigate failure modes of Proximal Policy Optimisation (PPO) under self-play. A first agent trained for $84{,}000$ episodes achieves only $26.8%$ win rate against a uniformly-random opponent in a symmetric zero-sum game. Through controlled ablations we identify five implementation-level failure modes — reward-scale imbalance, missing terminal signal, ineffective long-horizon credit assignment, unnormalised observations, and […]

Ver mais

Fully observable Matsuzawa puzzles are grid worlds where an agent must pick up coins in a particular order, travel down a long hallway, then pick up coins in order again. The secondary chamber has the coins in exactly the locations in which they occurred in the primary. https://i.imgur.com/5nvi0oe.png coins must be picked up in the order of their face number. coins in the secondary chamber are pickable only when there are no coins remaining in the primary. reward […]

Ver mais

arXiv:2603.28901v1 Announce Type: new Abstract: The proverb “see something, say something” captures a core responsibility of autonomous mobile robots in safety-critical situations: when they detect a hazard, they must communicate–and do so quickly. In emergency scenarios, delayed or miscalibrated responses directly increase the time to action and the risk of damage. We argue that a systematic context-sensitive assessment of the criticality level, time sensitivity, and feasibility of mitigation is necessary for AMRs to reduce time to action and […]

Ver mais

arXiv:2602.15082v1 Announce Type: new Abstract: Neural audio compression models have recently achieved extreme compression rates, enabling efficient latent generative modeling. Conversely, latent generative models have been applied to compression, pushing the limits of continuous and discrete approaches. However, existing methods remain constrained to low-resolution audio and degrade substantially at very low bitrates, where audible artifacts are prominent. In this paper, we present S-PRESSO, a 48kHz sound effect compression model that produces both continuous and discrete embeddings at ultra-low […]

Ver mais

This paper investigates the Restless Multi-Armed Bandit (RMAB) framework under individual penalty constraints to address resource allocation challenges in dynamic wireless networked environments. Unlike conventional RMAB models, our model allows each user (arm) to have distinct and stringent performance constraints, such as energy limits, activation limits, or age of information minimums, enabling the capture of diverse objectives including fairness and efficiency. To find the optimal resource allocation policy, we propose a new Penalty-Optimal Whittle (POW) index policy. The […]

Ver mais

arXiv:2603.02212v1 Announce Type: new Abstract: Tabular reasoning benchmarks mix semantic inference, numerical computation, and brittle table formatting, yet evaluations for small models remain vulnerable to contamination, dataset artifacts, and retrieval failures. We propose GLEAN, a lightweight evaluation protocol that integrates contamination-aware probes, weak-supervision governance, retrieval-reasoning diagnostics, and structured error attribution under tight hardware constraints. We evaluate across TabFact, WTQ via Squall, TableBench, RobuT, and SciTab under a 16GB GPU budget. Using Squall gold SQL as an executable anchor […]

Ver mais

Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent variables. To facilitate the development and evaluation of these models, a variety of synthetic and real-world datasets have been proposed, each with distinct advantages and limitations. For practical applications, CRL models must perform robustly across multiple evaluation directions, including reconstruction, disentanglement, causal discovery, and counterfactual reasoning, using […]

Ver mais

The Cloudflare developer platform is excellent. The tooling gap is real. Cloudflare’s developer platform has matured significantly. D1 gives you a SQLite-compatible serverless database running at the edge. R2 offers S3-compatible object storage with zero egress fees. Workers KV delivers globally replicated key-value reads with single-digit millisecond latency. Cloudflare Images handles upload, optimization, transformation, and delivery via a CDN; all through a single API. The platform is genuinely capable. What it lacks is a decent local development experience […]

Ver mais