al-folio

a simple whitespace theme for academics

Some posts are currently under review and may be updated.

rl Policy Improvement Theorem

7 min read · April 07, 2024

2024 · reinforcement-learning policy-gradient · reinforcement-learning
rl The Policy Gradient Family: PG, PPO, and AC

94 min read · March 13, 2024

2024 · reinforcement-learning · reinforcement-learning
rl Bellman Operator Identities

14 min read · February 18, 2024

2024 · reinforcement-learning bellman-operator · reinforcement-learning
llm Mixture of Experts Explained

22 min read · December 16, 2023

2023 · language-model architecture · lm-optimization
Ilya Sutskever: An Observation on Generalization

22 min read · August 15, 2023

2023 · language-models generalization statistics · talks