An all-in-one project for humanoid robots from locomotion to motion tracking.

Teleoperation solutions for UFACTORY robotic arms like Lite 6, xArm 5/6/7 and 850

Reinforcement Learning for Fault-Tolerant Quantum Circuit Discovery

Contains information links, articles, research papers, tweets, blog posts, companies etc and everything which is even minutely related to the field of Artificial Intelligence, Distributed Computing, Quantum Computing and Physics, Evolutionary Biology, Crypto-currency, Virual and Augmented Reality etc.

This is repository for GOAT experiments on multi agent overcooked environment.

Research Project in collaboration with BlockHouse

🚖 A hybrid Machine Learning + Reinforcement Learning project that predicts dynamic ride pricing. Combines historical ride data (ML) with a Q-learning agent (RL) to recommend fair, adaptive prices based on demand, supply, and customer loyalty.

Dashboard for real-world inspired environment for selective context retention under noise. It evaluates an LLM's ability to manage a fixed-capacity memory buffer, retaining high-value information while filtering out distractors

A hybrid Evolutionary Computation (EC) and Reinforcement Learning (RL) framework for simulating and mitigating housing price volatility via macroeconomic policy control.

This service is designed to centralize and streamline communication between an agent in reinforcement learning and services on Kind Kubernetes, thereby preventing circular dependencies in software architecture, and making maintenance easier.

This repo is an adaptation of UC Berkeley's project and focuses on developing search algorithms and reinforcement learning techniques for artificial agents. The code covers related topics and can be used for further exploration in the field of AI.

[ICMLA' 2022] IGN : Implicit Generative Networks

A research sandbox for LLM pretraining, fine-tuning (SFT, DPO, RLHF), and alignment techniques. Designed for developing LLM-based solutions in computational biology.

This project provides a reinforcement learning-based framework for optimizing traffic flow at complex urban intersections. A Deep Q-Learning agent is trained to intelligently control traffic signal phases in order to minimize congestion and waiting times, ultimately improving traffic efficiency.

Implementation of early deep reinforcement learning algorithms such as Vanilla DQN, Double DQN, and Dueling DQN.

Reinforcement learning solution for snake game

Experience gaming evolution with Autonomous PacBot: a Reinforcement Learning-powered Pacman agent.