Pradyot Bathuri@pbathuri
is under improvement
6
Events attended
2
Submissions made
1 year of experience
About me
Hello, my name is Pradyot, I am great at making coffee and sitting long sessions making trading algorithms after drinking that Coffee. I have worked on 4 medium-sized algorithm development projects so far, and I am good at in a Python workspace and intuitive at statistical modelling. I am passionate about many subjects intersecting with ML, but right now I am looking at quantum mechanics and its stochastic capability to model an ML model to pioneer a new model or at least the research towards it. I also love big old red buildings, especially if it's a library or an old artillery depot, that nostalgic feeling with an old note of smell to it as I walk in is just indescribable.
is under improvement
š¤ Latest Submissions
RoboDk based Quantum state simulator
The QuantumāEnhanced Robotics Simulator (QERS) is a fullyāfunctional digital testbed for designing, testing and validating robotic systems without physical hardware. Our goal is to narrow the reality gap between simulation and the real world by combining deterministic macroāphysics from engines like PyBullet with a quantumāstochastic plugin that injects realistic noise via Qiskit. The simulator supports deterministic, stochastic and quantumāperturbed stepping modes and exposes a FastAPI REST API for running jobs, retrieving metrics and managing assets. A Celery/Redis job system queues and executes simulation runs asynchronously, while the Next.js/Three.js web application provides a realātime dashboard with a 3D viewport, scene tree, metrics panel and controls to toggle between classical domain randomization and quantum noise. Reality profiles define configurable dynamics, sensor and actuation parameters, enabling multiāprofile evaluation of policies. QERS computes gap metrics such as G<sub>dyn</sub>, G<sub>perc</sub> and G<sub>perf</sub> and includes scripts for benchmarking across profiles and generating reports. Users can import URDFs, run batch simulations and compute performance drops and rank stability. Future phases will add mesh segmentation, an AIādriven textātoāalgorithm pipeline for generating planner and controller skeletons, and neuralāaugmented simulation informed by real data. By combining quantum computing, domain randomization, residual learning and modern web technologies, QERS demonstrates a practical path to simātoāreal transfer and a productionāminded robotics startup.
15 Feb 2026
Captain Whiskers - A Trustless-Quantum-Aware Agent
Captain Whiskers demonstrates what it truly means to place real money under the control of an autonomous AIāwithout sacrificing trust, security, or accountability. As AI agents increasingly make financial decisions, the core challenge is no longer intelligence, but trust. Captain Whiskers solves this by combining Gemini-powered reasoning, quantum-inspired optimisation, and decentralised verification to create a treasury agent that is both autonomous and provably safe. Users interact with the system via a clean, high-performance trading interface inspired by modern platforms like Robinhood and Webull. High-level goals such as risk tolerance, allocation targets, or execution constraints are translated by Gemini into structured financial actions. Portfolio optimisation is performed using quantum algorithms (VQE via Qiskit), modelling multiple portfolio states simultaneously to identify optimal risk-return tradeoffs. Every decision is then passed through a trustless verification layer: an independent network of 11 verifiers evaluates the agentās logic, risk checks, and cryptographic proofs. Only when a Byzantine Fault Tolerant quorum (7/11) is reached does execution proceed. This ensures decisions are not manipulated or hallucinated, or silently altered. Execution and settlement occur on the Arc testnet using USDC, powered by Circle Developer-Controlled Wallets and Circle Gateway. The system integrates post-quantum cryptography (CRYSTALS-Dilithium) and quantum-grade randomness to remain secure in a future where classical cryptography is failing. By combining Circleās USDC infrastructure, Arcās execution layer, and Geminiās reasoning capabilities, Captain Whiskers showcases a credible future where AI agents can safely manage value at scale, earning trust not through promises, but through math, cryptography, and transparent on-chain proof.
24 Jan 2026
