Skip to main content

Others

MCMC - Markov Chain Monte Carlo

https://skymind.ai/wiki/markov-chain-monte-carlo

Bayesian approach

In the Bayesian approach to decision-making, you first start with the prior, this is what your beliefs are, then as data comes in, you incorporate that data to update these priors to get the posterior.

Bayesian Model

A Bayesian model is a statistical model where you use probability to represent all uncertainty within the model.

https://www.toptal.com/algorithms/metropolis-hastings-bayesian-inference

AlphaGO​

  1. Policy Network

  2. Value Network

  3. Tree Search

Q-Learning: an algorithm which produces a Q-table that an agent uses to find the best action to take given a state.

Deep Q Neural Network​

A Neural Network that takes a state and approximates Q-values for each action based on that state.

Asynchronous Actor-Critic Agent​

https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c-c88f72a5e9f2