digitado

I’ve been working on a reinforcement learning project focused on trading using recurrent architectures, and I’ve open-sourced it for learning and discussion. Repo: https://github.com/TiwariLaxuu/Recurrent-RL-in-Trading- The idea is to explore how recurrent models (RNN/LSTM-style components) can be integrated into RL agents for financial decision-making, especially in sequential market environments. Feel free to check it out, give feedback, or suggest improvements. If you find it useful, a star would really help support the work and motivation to keep improving it. […]

Ver mais

I have a paper accepted at a non-archival ICML workshop this year, and I am trying to decide whether it is worth registering and attending. By coincidence, I will already be in Seoul around that time, but I would have to pay the workshop registration fee (~$400) out of my own pocket. I would only be registering for the workshop day since I have other commitments during the rest of the conference. I am thinking of applying to […]

Ver mais

Real estate has always been about location, timing, and relationships. In 2026, it is also about intelligence. Behind every fast property match, Softprodigy company optimized price recommendation, predictive maintenance alert, or instant lead response, there is something more powerful at work than traditional automation. There are conversational ai in real estate systems making decisions, coordinating workflows, and continuously improving outcomes. Agentic AI is no more just experimental in real estate. It is actively reshaping how firms generate revenue, […]

Ver mais

Representation learning is central to modern machine learning, enabling transitions from handcrafted features to learned embeddings, latent spaces, foundation models, world models, and digital twins. Yet most research examines how representations are optimized after a representational framework has been selected, while less attention is given to when a new level of representation becomes necessary. We introduce the Bootstrap Theory of Representational Emergence (TBER), a framework describing how new representations arise when existing ones become explanatorily insufficient. In this […]

Ver mais

About 10 years ago, I got into the basics of ML (like regression, KNN’s, LVQ’s) and read a few papers before taking a break a few years back. It feels like now, there’s a lot of researchers in AI. How do you identify the ones who are actually solid vs those who (forgive my phrasing) are more researchers for appearance/status (i.e don’t actually know what they’re talking about)? Is the core filter h-index or where they work? How […]

Ver mais

Before you dive in: AI workflows aren’t plug-and-play, they need thoughtful prompts, clean inputs, and human review gates. Think of each workflow as a junior collaborator, not a vending machine. The 60% figure represents execution automation, not decision-making. Strategy, judgment, and relationships still live with your team. AI workflows change that equation entirely. By connecting the right tools in the right sequence, you can build autonomous pipelines that handle the work between decisions — freeing your team to do the work […]

Ver mais

I did my MEng at Imperial building a massively GPU parallelized sim for drone RL, thousands of episodes stepping at once on the GPU. The thing that surprised me most was that simulation throughput dominated almost everything, wall clock, iteration speed, and cost, far more than the algorithm work. Now I want to know whether that is universal or just my niche. Genuine question to anyone running real RL training (robotics, embodied, games, whatever). What is the single […]

Ver mais