Essays and working notes on LLM post-training, distillation, RL and efficient inference.https://alzantot.me/en-ushttps://medium.com/@m.alzantot/deep-reinforcement-learning-demysitifed-episode-2-policy-iteration-value-iteration-and-q-978f9e89ddaahttps://medium.com/@m.alzantot/deep-reinforcement-learning-demysitifed-episode-2-policy-iteration-value-iteration-and-q-978f9e89ddaaMarkov decision processes, then value iteration and policy iteration for when the environment is known, and Q-learning for when it is not.Sun, 09 Jul 2017 00:00:00 GMTreinforcement-learningq-learninghttps://medium.com/becoming-human/genetic-algorithm-for-reinforcement-learning-a38a5612c4dchttps://medium.com/becoming-human/genetic-algorithm-for-reinforcement-learning-a38a5612c4dcUsing a genetic algorithm, a gradient-free evolutionary method, to solve the Frozen Lake problem in OpenAI Gym.Wed, 07 Jun 2017 00:00:00 GMTreinforcement-learninggenetic-algorithmshttps://medium.com/@m.alzantot/deep-reinforcement-learning-demystified-episode-0-2198c05a6124https://medium.com/@m.alzantot/deep-reinforcement-learning-demystified-episode-0-2198c05a6124What reinforcement learning is, how to install and run OpenAI Gym, and solving Cart-Pole with a simple random policy search.Thu, 27 Apr 2017 00:00:00 GMTreinforcement-learningopenai-gymhttps://malzantot.blogspot.com/2014/07/tips-for-computer-science-junior.htmlhttps://malzantot.blogspot.com/2014/07/tips-for-computer-science-junior.htmlAdvice, 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.Sat, 19 Jul 2014 00:00:00 GMTcareerstudents