Python utilities to compute a lower bound of the expected sample complexity to identify the best arm in a bandit model
-
Updated
Sep 8, 2021 - Python
Python utilities to compute a lower bound of the expected sample complexity to identify the best arm in a bandit model
This is a collection of interesting papers that I have read so far or want to read. Note that the list is not up-to-date. Topics: reinforcement learning, deep learning, mathematics, statistics, bandit algorithms, optimization.
Randomized Greedy Learning Under Full-bandit Feedback
Repository contains codes for the course CS780: Deep Reinforcement Learning
Several multi-armed bandit strategies with additional holding option for smoother exploration.
Reinforcement Learning (COMP 579) Project
💫 Fast Julia implementation of various Kullback-Leibler divergences for 1D parametric distributions. 🏋 Also provides optimized code for kl-UCB indexes
a collection of google colab notebooks with educational stuff about bandits and their variations
An illustrative project including some multi-armed bandit algorithms and contextual bandit algorithms
Bandit and Evolutionary Algorithms using Python
🎩🤠Some Bandit Algorithms in Typescript
2024 ICML Official code
Ads Click-through rate using thompson sampling
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms
An Implementation of the N-Tuple Bandits Evolutionary Algorithm.
Programming assignments completed for my Reinforcement Learning course: Topics include Bandit Algorithms, Dynamic Programming, policy iteration, Monte-Carlo methods, SARSA, Q-Learning, Dyna-Q/Dyna-Q+, gradient control methods, state aggregation methods, and Deep Q-Learning Networks (DQNs).
Pricing and advertising strategy for the e-commerce of an airline company, based on Multi-Armed Bandits (MABs) algorithms and Gaussian Processes. Simulations include non-stationary environments.
🐯REPLICA of "Auction-based combinatorial multi-armed bandit mechanisms with strategic arms"
Implementation for NeurIPS 2020 paper "Locally Differentially Private (Contextual) Bandits Learning" (https://arxiv.org/abs/2006.00701)
Add a description, image, and links to the bandit-algorithms topic page so that developers can more easily learn about it.
To associate your repository with the bandit-algorithms topic, visit your repo's landing page and select "manage topics."