Writing
Notes on post-training specialized language models, reinforcement learning, and whatever else I'm thinking about. RSS.
- Deep Reinforcement Learning Demystified (Episode 2): Policy Iteration, Value Iteration and Q-learning
Markov decision processes, then value iteration and policy iteration for when the environment is known, and Q-learning for when it is not.
- Episode 1: Genetic Algorithm for Reinforcement Learning
Using a genetic algorithm, a gradient-free evolutionary method, to solve the Frozen Lake problem in OpenAI Gym.
- Deep Reinforcement Learning Demystified (Episode 0)
What reinforcement learning is, how to install and run OpenAI Gym, and solving Cart-Pole with a simple random policy search.
- Tips for Computer Science Junior Students[Arabic]
Advice, written in Arabic, for early-year computer science students aiming for a top tech company or graduate school: strengthen your English, master one programming language, practice, keep learning, and contribute.