Deep Reinforcement Learning
Stable Baselines rely on TF 1.x but Stable Baselines v3 rely on PyTorch.
Latest posts
See also all posts ordered by category or date.
AlphaGo and Alpha Zero
In December 2016 we presented it at ENS Paris-Saclay with Étienne Simon but apparently I never wrote a blog post in the end.
Six dates importantes en algorithmique
- -300
- Algorithme d’Euclide (qui date peut-être de l’école de Pythagore 530 av. J.C.)
Quadrangle Inequality trick for dynamic programs
Application: Given an ordered list of keys with frequencies, build a binary search tree on those keys which minimizes the average query cost.
Pareto optimality
Compute the pareto set of a given set of points in 2 or 3 dimensions.
Multiplying polynomials
You are given two polynomials $P$ and $Q$ and want to compute their product. The polynomials are given in form of an array with their coefficients.
Making pairs adjacent at minimal cost
You are given an array $X$ with the promise that each of its values appears exactly twice. You want to transform $X$ such that at the end all pairs are adjacent in the array. An allowed operation consists in removing a value from $X$ and appending it at the end. The cost of a solution is the maximal value which was moved.
Identifying the maximum in a sliding window
Given an array $x$ and an integer $k$, determine for every index $1 \leq j\leq n$ the maximum $x[i]$ among all indices $\max\{1,j-k+1 \} \leq i \leq j$.
Maintaining sum of k largest items in a dynamic set
Maintain a set, allowing to add or remove elements and to query the sum of the up to k largest items.