Blog

This post explains Trust Region Policy Optimization (TRPO) and shows how it addresses common issues in vanilla policy gradient methods.

This post is an intro to reinforcement learning, in particular, Monte Carlo methods, Temporal Difference Learning, Deep Q-learning, Policy Gradient methods, and Advantage Actor-Critic.

This post introduces vector databases with Milvus, an open-source vector data management system to efficiently store and search large-scale and dynamic vector data.

In this post, we will cover word embeddings, an approach in NLP for representing text as real value vectors that capture complex relationships between words and phrases.

This post explores the process of Byte-Pair Encoding, from handling raw training text and pre-tokenization to constructing vocabularies and tokenizing new text.

This post examines N-body simulations using the Barnes-Hut algorithm and its parallel implementation in CUDA. We will first cover the basics of N-body simulation and the Barnes-Hut Algorithm, then move on to its parallelized implementation.

In this post, we take a deep dive into the Raft consensus algorithm, essential for distributed systems. We explore key mechanisms like leader election, log replication, and safety, plus aspects like cluster membership changes, log compaction, and client interactions.