e-greedy

There are 0 repository under e-greedy topic.

• n4i9kita / ExploratoryProject

  Analysis of various multi armed bandit algorithms over normal and heavy-tailed distributions.

  multi-armed-banditsmultiarmed-banditsreinforcement-learninge-greedynormaldistr
  Language:Jupyter Notebook 0

• OrestisMk / RF-Q_learning-taxi_driver--Lunanlander-Policy-gradient-

  This is a project of reinforcement learning which contains two different environments. The first environment is the taxi driver problem in 4x4 space with the simple Q-learning update rule. In this task, we compared the performance of the e-greedy policy and Boltzmann policy. As a second environment, we chose the LunarLander from the open gym. For the implementation of the project, the Policy gradient has been selected.

  reinforcement-learningq-learninge-greedyboltzmann-explorationpolicy-gradienttaxi-driverlunarlander-v2
  0

• Stepan-Makarenko / Multi-armed-bandit-research

  e-greedymulti-armed-banditsucb1
  Language:Jupyter Notebook 0

• JoelJa835 / MAB_Algorithms

  Implementation of Multi-Armed Bandit (MAB) algorithms UCB and Epsilon-Greedy. MAB is a class of problems in reinforcement learning where an agent learns to choose actions from a set of arms, each associated with an unknown reward distribution. UCB and Epsilon-Greedy are popular algorithms for solving MAB problems.

  banditse-greedymabreinforcement-learning-algorithmsucb
  Language:Python

• Murtazali05 / Multi-armed-bandit

  Multi Armed Bandits implementation using the Jester Dataset

  e-greedymulti-armed-banditsthompson-samplingucb
  Language:Python

• tatiana-boura / MSc-in-AI-Demokritos-Reinforcement-Learning-Course

  Implementation of an Q-learning, ϵ-greedy agent that learns how to play the game with the other agents he is connected to.

  e-greedymultiagent-systemsq-learningreinforcement-learning
  Language:Python