efavdb

New post: Generalized dollar cost averaging efavdb.com/generalized_do…

new post: efavdb.com/duality

how to price dividend stocks efavdb.com/pricing-divide…

New post: Utility engines efavdb.com/utility-engines

@OpenAI has has opened applications for their 4th Scholars program -- it looks better than ever! jobs.lever.co/openai/90311c5…

2+1 = 4, by quinoa efavdb.com/quinoa%20packi…

Blog post with code to generate real time policy and value function plots while actor critic RL agent is interacting with environment: efavdb.com/visualize-acto…

We put together resources to get started in #reinforcementlearning at efavdb.com/pages/rl-resou…, including observations from our own experience with them in the @OpenAI Scholars 2020 program. May this boost the sample efficiency of other learners! 💪

2D random walks are special: efavdb.com/random-walk-sc…

@koeppelmann @CiesekSandra Write up on optimal reduction in tests per person via binary search pooling: github.com/EFavDB/pooling…

since many are asking: the article did not provide details about the exact method. In the article, they talked only about pools of 5 but that would not allow a 10x scale factor. So I assumed pools of 16 in my Tweet. Maybe @CiesekSandra can share more details.

New blog post about Q-learning and DQN! #ReinforcementLearning

@coleloco How did you get the test?

Write up of an old idea for reducing test counts needed to screen for disease: Pooling of samples. Written up here to promote what might be a good idea in some circumstances. github.com/EFavDB/pooling

New post using dynamic programming to solve a toy #reinforcementlearning problem efavdb.com/reinforcement-…

New post introducing #ReinforcementLearning with a toy problem efavdb.com/intro-rl-toy-e… using @OpenAI gym environment

A new post about a simulation framework for exploring population dynamics, natural selection, game theory, and more: efavdb.com/world-wanderin…

New post about multiarmed bandits in the context of reinforcement learning: efavdb.com/multiarmed-ban…

New post from starting in the Spring 2020 cohort of the #OpenAI Scholars program: efavdb.com/openai-scholar…

New post: "Universal limiting mean return of CPPI investment portfolios" This is a sort-of central-limit-theorem like result that holds in some cases for investment portfolios subject to portfolio insurance. See below. efavdb.com/universal-mean…

New post: Universal drawdown statistics in investing efavdb.com/universal-draw…