Questions on Guided Policy Search

I’ve been reading Prof. Sergey Levine‘s paper on Guided Policy Search (GPS) [2]. However, I do not understand about it but want to have a record of my questions so maybe in the future I could look back and solve. Based on my understanding, traditional policy search (e.g., REINFORCE) maximizes the likelihood ratio of rewards. This …

Relationships between DP, RL, Prioritized Sweeping, Prioritized Experience Replay, etc

In the last weekend, I’ve struggled with many concepts in Reinforcement Learning (RL) and Dynamic Programming (DP). In this post, I am collecting some of my thoughts about DP, RL, Prioritized Sweeping and Prioritized Experience Replay. Please also refer to a previous post written when I first learned RL. Let’s first introduce a Markov Decision …

tricks in deep learning neural network

In this post, I am going to talk my understanding in tricks in training deep neural network. ResNet [1] Why does ResNet network work? https://www.quora.com/How-does-deep-residual-learning-work Here is my answer: It is hard to know the desired depth of a deep network. If layers are too deep, errors are hard to propagate back correctly. if layers are …

A3C code walkthrough

In this post, I am doing a brief code walkthrough for the code written in https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c-c88f72a5e9f2 The code implements A3C algorithm (Asynchronous Methods for Deep Reinforcement Learning). It follows the pseudocode given in supplemental part in the paper: The structure of this model is: For LSTM structure detail, refer to http://colah.github.io/posts/2015-08-Understanding-LSTMs/. I am using the same …

Policy Gradient

Reinforcement learning algorithms can be divided into many families. In model-free temporal difference methods like Q-learning/SARSA, we try to learn action value for any state-action pair, either by recording (“memorizing”) exact values in a tabular or learning a function to approximate it. Under -greedy, the action to be selected at a state will therefore be  but there …