Archives: 2020/1

Since 2024-09-02, this blog has been stopped to be updated. For newer contents, please go to fuguirong.de.

Keep Growing

2020

The data is assumed to be drawn from some distributions. In reinforcement learning, we learn by interacting with environ

2020-01-29 Learning Notes

AI Reinforcement Learning Bayesian

Before, we talk about static models, which means variables don’t change possible values. For temporal models, in which v

2020-01-28 Learning Notes

AI Reinforcement Learning Bayesian Markov

How do we use inference we keep tracking over time in order to act? Markov Decision ProcessAn essential model studied i

2020-01-28 Learning Notes

AI Reinforcement Learning Markov

So far, we talk about how to use a given model to do some tasks, e.g. inference, planning. But where do these models com

2020-01-28 Learning Notes

AI Reinforcement Learning Bayesian

InferenceTypical queries What are these typical queries for? what kinds of typical queries? conditional/marginal query:

2020-01-26 Learning Notes

AI Reinforcement Learning Bayesian

Fundamental SettingsUse Agent-environment model to represent all tasks. Agenthas a set $A$ and a function $f$. $A$: th

2020-01-23 Learning Notes

AI Reinforcement Learning Probability Theory

Questions why to say the conditional independence is weaker than independence? what are the properties of conditional in

2020-01-23 Learning Notes

AI Reinforcement Learning Bayesian

I took part in the course Probabilistic Artifical Intelligence in the autumn festival 2019, which is opened by the super

2020-01-23 Sharing

AI Reinforcement Learning

PrefaceIn 2019 fall semester, I took part in the course Advanced algorithms, opened by Mohsen Ghaffari, ETH Zurich. Mohs

2020-01-22 Sharing

Algorithm